Spaces:
Running
Running
| import streamlit as st | |
| from PIL import Image | |
| from streamlit_lottie import st_lottie | |
| import json | |
| import os | |
| import glob | |
| from streamlit_option_menu import option_menu | |
| from projects import display_projects | |
| #setting layout to wide | |
| st.set_page_config(layout="wide") | |
| # Load CSS for styling with a minimalist grey background | |
| with open("style.css") as f: | |
| css_content = f.read() | |
| css_content += ''' | |
| body { | |
| background-color: #f0f2f6; | |
| } | |
| ''' | |
| st.markdown('<style>{}</style>'.format(css_content), unsafe_allow_html=True) | |
| def load_lottiefile(filepath: str): | |
| with open(filepath, "r") as file: | |
| return json.load(file) | |
| def display_header(): | |
| st.write(''' | |
| # Nihar Palem | |
| ##### | |
| ''') | |
| # Assuming you have a Lottie animation to display | |
| lottie_animation = load_lottiefile("bio.json") | |
| st_lottie(lottie_animation, height=300, key="header_animation") | |
| def display_summary(): | |
| #st.markdown('## Summary', unsafe_allow_html=True) | |
| st.markdown(""" | |
| Hello! I'm **Sai Nihar Reddy Palem**, an Applied AI Engineer, Data Scientist, and AI Researcher based in San Jose, California. Originally from Hyderabad, India, I've embarked on a transformative journey from Electrical Engineering to becoming a passionate AI researcher exploring the frontiers of artificial intelligence. | |
| My path began with a solid engineering foundation, evolved through diverse industry experiences across data engineering and analytics, and reached new heights with my **Master's degree in Applied Data Science** from San Jose State University. Over the past 2+ years, I've immersed myself in the cutting-edge world of multimodal AI, Large Language Model fine-tuning, and multi-agent architectures, consistently pushing the boundaries between theoretical research and practical implementation. Currently, I'm working with Google on bettering their multimodal capabilities, contributing to the advancement of state-of-the-art AI systems. | |
| What drives me is the exciting challenge of systematically translating breakthrough research papers into production-ready solutions that create real-world impact. From achieving 12% performance improvements through advanced LLM optimization techniques to actively participating and learning from technical events like hackathons where I've built innovative multi-agent systems in just 5 hours (most recent), my journey reflects a deep commitment to both research excellence and practical innovation. I've contributed to open-source projects that have garnered 10,000+ community interactions, developed comprehensive evaluation frameworks for state-of-the-art models like Gemini 3.0, and created an applications that democratize AI technology for businesses and individuals alike. | |
| **What You'll Find in This Portfolio**: Education, Work Experience, Projects, Skills, Research Notes, Social Media, Open Source Applications, Awards | |
| """) | |
| def display_education(): | |
| st.markdown('## Education') | |
| st.write(""" | |
| - **Masters In Data Analytics**, *San Jose State University*, USA (2023-2024) | |
| - Courses: Data Mining, Deep Learning, Big Data Technologies, Data Visualization, Machine Learning, Database Management Systems | |
| - Achievements: | |
| - A Grade in Deep Learning | |
| - **Bachelor of Technology (B.Tech) in Electrical and Electronics Engineering (EEE)**, *Sreenidhi Institute of Science and Technology (SNIST)*, Hyderabad (2015-2019) | |
| - Activities: | |
| - Memeber of the Robotics Club:, built line follower and theft-alert detection bots. | |
| - Member of the college cricket team; Runner up in City-level tournament | |
| """) | |
| def display_work_experience(): | |
| st.markdown('## Work Experience') | |
| st.write(""" | |
| **Turing, San Jose, CA, USA** | |
| March 2024 - Present | |
| - **Data Scientist & Applied AI Engineer** | |
| - Collaborated with AI engineers, product teams, researchers, and Google DeepMind team to integrate LLM evaluation systems into production workflows using PyTorch and distributed computing | |
| - Engineered comprehensive evaluation benchmarks for Gemini 3.0 by analyzing reasoning loss patterns and image loss patterns in state-of-the-art Vision-Language Models (VLMs) including o3 and Gemini 2.5 Pro, developing custom datasets across multiple domains (mathematics, finance, chemistry, biology) spanning educational levels from high-school through PhD with statistical validation methods | |
| - Implemented advanced LLM fine-tuning strategies for Qwen model including Parameter-Efficient Fine-Tuning (PEFT) with LoRA and 2-stage whole model training on multi-GPU clusters, achieving 12% performance improvement across 15+ categories | |
| - Developed "auto hinter" system to improve LLM reasoning, guiding models towards correct answers based on question complexity, resulting in 8% performance increment on PhD-level questions | |
| - Built "auto rater" system to assess responses from leading models like Gemini 2.5 Pro and o3 custom builds, scoring across four key dimensions: completeness, coherence, clarity, correctness, style and formatting | |
| **San Jose State University, San Jose, CA, USA** | |
| August 2024 - December 2024 | |
| - **Teaching Assistant** | |
| - Mentored 80+ graduate students on data modeling projects, providing feedback on technical documentation | |
| - Reviewed and debugged student data pipelines, offering solutions for data analysis and ML model challenges | |
| - Improved student performance, with 75% of mentored students achieving an 'A' grade | |
| -Conducted weekly office hours to assist students with complex data science concepts and project implementations | |
| **Bharat Electronics Limited, Hyderabad, India** | |
| February 2021 - March 2022 | |
| - **Data Analyst** | |
| - Optimized SQL queries for sales and payroll databases using indexes and CTEs, reducing execution times by 40% | |
| - Developed and maintained 20+ Tableau dashboards, reducing production costs by 15% and improving sales forecasts by 10% | |
| - Implemented automated billing checks using SQL procedures, reducing financial discrepancies by 30% | |
| - Optimized ETL pipelines with staging tables and data quality checks, increasing ingestion efficiency by 25% | |
| **Technical Writer** | |
| 2023-Present | |
| - Embarked on a new journey in 2023 as a technical writer, sharing insights and developments in data science and data engineering with a growing audience. | |
| - Authored numerous articles that explore complex topics in an accessible and informative manner, focusing on AI, data science, machine learning and data engineering. | |
| - This new habit aims to educate and inspire, bridging the gap between technical expertise and practical application in the modern data landscape. | |
| - Find my work on [Medium](https://medium.com/@nihar-palem) and [Substack](https://niharpalem.substack.com/publish/posts). | |
| """) | |
| def display_skills(): | |
| st.title('Skills') | |
| # Define tab titles | |
| tab_titles = [ | |
| "Programming & Core", | |
| "AI & ML", | |
| "Data Engineering", | |
| "Data Architecture", | |
| "Visualization", | |
| "Specialized Systems", | |
| "Multimodal AI", | |
| "LLM & Advanced AI" | |
| ] | |
| # Create tabs | |
| tabs = st.tabs(tab_titles) | |
| # Programming & Core Technologies | |
| with tabs[0]: | |
| st.subheader("Programming & Core Technologies") | |
| st.markdown(""" | |
| - **Programming Languages**: | |
| - Python (Advanced) | |
| - SQL (Advanced) | |
| - Shell Scripting | |
| - **Database Systems**: | |
| - Relational: MySQL, PostgreSQL | |
| - NoSQL: MongoDB | |
| - Data Warehouses: Snowflake, Redshift | |
| - Vector Databases: FAISS, Pinecone | |
| - **Development Tools**: | |
| - Version Control: Git, GitHub | |
| - Containerization: Docker | |
| - Orchestration: Kubernetes (Basic) | |
| - IDE: VS Code, PyCharm | |
| - Microsoft Office Suite | |
| - **Frameworks & Libraries**: | |
| - LangChain | |
| - Hugging Face (Transformers, Diffusers) | |
| - Scikit-Learn, Pandas, NumPy | |
| - Apache Spark | |
| """) | |
| # AI & Machine Learning | |
| with tabs[1]: | |
| st.subheader("AI & Machine Learning") | |
| st.markdown(""" | |
| - **Machine Learning Frameworks**: | |
| - PyTorch (Advanced, PyTorch Distributed, DDP) | |
| - TensorFlow | |
| - Scikit-Learn | |
| - XGBoost, Random Forest, AdaBoost | |
| - **Deep Learning**: | |
| - Vision Transformers (ViT) | |
| - Vision Language Models | |
| - Large Language Models | |
| - Sentecne Transformers | |
| - Diffusion Models | |
| - ResNet Architectures | |
| - Neural Networks | |
| - BiLSTM | |
| - **Distributed Training**: | |
| - Multi-GPU Clusters (16+ GPUs) | |
| - PyTorch DDP (Distributed Data Parallel) | |
| - DeepSpeed | |
| - Megatron | |
| - CUDA Acceleration | |
| - FlashAttention | |
| - **Computer Vision**: | |
| - MediaPipe | |
| - OpenCV | |
| - Image Processing Pipelines | |
| - Satellite Imagery Analysis | |
| - **Model Optimization**: | |
| - Model Compression (Quantization, Distillation) | |
| - Performance Optimization | |
| - CUDA Programming | |
| - Parallel Processing | |
| """) | |
| # Data Engineering & Cloud | |
| with tabs[2]: | |
| st.subheader("Data Engineering & Cloud") | |
| st.markdown(""" | |
| - **Cloud Platforms**: | |
| - AWS (Certified - Lambda, S3, Glue, EC2, Redshift) | |
| - Google Cloud Platform (GCP) | |
| - Cloud Architecture Design | |
| - **Big Data Technologies**: | |
| - Apache Spark (PySpark) | |
| - Apache Airflow | |
| - BigQuery | |
| - Hadoop Ecosystem | |
| - **Data Pipeline Tools**: | |
| - ETL/ELT Pipeline Design | |
| - Workflow Orchestration | |
| - Concurrent Processing | |
| - Real-time Data Streaming | |
| - ThreadPoolExecutor Optimization | |
| - **Infrastructure**: | |
| - CI/CD Pipelines (GitHub Actions) | |
| - Infrastructure as Code | |
| - Kubernetes Basics | |
| - Production Monitoring | |
| - Distributed Training Clusters | |
| """) | |
| # Data Architecture & Analytics | |
| with tabs[3]: | |
| st.subheader("Data Architecture & Analytics") | |
| st.markdown(""" | |
| - **Data Modeling**: | |
| - OLAP/OLTP Systems | |
| - Star/Snowflake Schema | |
| - Data Normalization | |
| - Database Optimization | |
| - **Analytics Techniques**: | |
| - Streaming Analytics | |
| - Batch Processing | |
| - Time Series Analysis | |
| - Statistical Analysis | |
| - A/B Testing | |
| - Hypothesis Testing | |
| - **Data Processing**: | |
| - Pandas, NumPy | |
| - Data Wrangling | |
| - Feature Engineering | |
| - Data Quality Assurance | |
| - Data Quality Management | |
| - **Performance Optimization**: | |
| - Query Optimization | |
| - Indexing Strategies | |
| - Caching Mechanisms | |
| - SQL Performance Tuning | |
| """) | |
| # Visualization & Deployment | |
| with tabs[4]: | |
| st.subheader("Visualization & Tools") | |
| st.markdown(""" | |
| - **Business Intelligence**: | |
| - Tableau | |
| - Power BI | |
| - Dashboard Design | |
| - KPI Monitoring | |
| - **Technical Visualization**: | |
| - Plotly | |
| - Seaborn | |
| - Matplotlib | |
| - Interactive Charts | |
| - **Deployment & Interface**: | |
| - Streamlit | |
| - Web Development | |
| - Hugging Face Spaces | |
| - **Collaboration Tools**: | |
| - JIRA | |
| - Notion | |
| - Git Workflow | |
| - Agile Methodologies | |
| """) | |
| # Specialized Systems | |
| with tabs[5]: | |
| st.subheader("Specialized Systems") | |
| st.markdown(""" | |
| - **Recommender Systems**: | |
| - Hybrid Filtering Techniques | |
| - Content-Based Filtering | |
| - Collaborative Filtering | |
| - Matrix Factorization (SVD) | |
| - **Ensemble Methods**: | |
| - Multi-model Consensus Systems | |
| - Classifier Combinations | |
| - Voting Systems | |
| - Stacking Implementations | |
| - **Performance Optimization**: | |
| - CUDA Acceleration | |
| - Parallel Processing | |
| - Resource Management | |
| - Scalability Design | |
| - **Custom Solutions**: | |
| - Natural Language Processing | |
| - Computer Vision Systems | |
| - Time Series Forecasting | |
| - Anomaly Detection | |
| - Real-time Web Scraping | |
| - Automated Data Quality Checks | |
| """) | |
| # Multimodal AI | |
| with tabs[6]: | |
| st.subheader("Multimodal AI") | |
| st.markdown(""" | |
| - **Vision-Language Models**: | |
| - Qwen-VL | |
| - Gemini Multimodal | |
| - Vision-Language Understanding | |
| - Cross-modal Fine-tuning | |
| - Multimodal Evaluation | |
| - **Visual AI**: | |
| - Visual Question Answering (VQA) | |
| - Vision Transformers (ViT) | |
| - Stable Diffusion XL | |
| - Generative AI (Vision) | |
| - Image-Text Alignment | |
| - **Multi-Agent Systems**: | |
| - Multi-Agent Multimodal Workflows | |
| - Strategic Agent Architecture | |
| - Visual Agent Integration | |
| - QA Agent Implementation | |
| - **Evaluation & Testing**: | |
| - Multimodal Benchmarking | |
| - Cross-modal Bias Detection | |
| - Performance Optimization | |
| - Adversarial Testing | |
| - Statistical Validation Methods | |
| """) | |
| # LLM & Advanced AI | |
| with tabs[7]: | |
| st.subheader("LLM & Advanced AI") | |
| st.markdown(""" | |
| - **Large Language Models**: | |
| - Fine-tuning (PEFT, LoRA, QLoRA) | |
| - 2-Stage Training | |
| - VLLM/LMMs | |
| - Qwen, LLaMA (Llama-3.1-8B), GPT Integration | |
| - **Advanced Techniques**: | |
| - Prompt Engineering (Advanced, Context Injection) | |
| - RAG (Retrieval-Augmented Generation) | |
| - LLM Evaluation Benchmarking | |
| - LLM-as-judge | |
| - Auto Hinter Systems | |
| - **Production AI Systems**: | |
| - Multi-Agent Systems | |
| - API Integration | |
| - Performance Optimization | |
| - Tenstorrent Hardware Utilization | |
| - MLOps | |
| - **Specialized Applications**: | |
| - Semantic Job Matching | |
| - Resume Generation | |
| - Marketing Campaign Automation | |
| - Infrastructure Change Detection | |
| - Exercise Pose Correction | |
| - **AI Testing & Validation**: | |
| - Unit/Integration Testing for AI | |
| - Offline Evaluation Frameworks | |
| - Model Validation | |
| - ROC Curve Analysis | |
| - RMSE Validation | |
| - Bias Mitigation | |
| """) | |
| def display_articles(): | |
| """Display articles from HTML files in the articles directory""" | |
| st.markdown('## Articles') | |
| # Define the articles directory path | |
| articles_dir = "articles" # You can change this path as needed | |
| # Check if articles directory exists | |
| if not os.path.exists(articles_dir): | |
| st.warning(f"Articles directory '{articles_dir}' not found. Please create the directory and add your HTML files.") | |
| st.info("Create an 'articles' folder in your project directory and add your HTML files there.") | |
| return | |
| # Get all HTML files from the articles directory | |
| html_files = glob.glob(os.path.join(articles_dir, "*.html")) | |
| if not html_files: | |
| st.info("No HTML articles found in the articles directory. Add some .html files to get started!") | |
| return | |
| # Sort files by name for consistent ordering | |
| html_files.sort() | |
| st.markdown("Click on any article below to view:") | |
| st.markdown("") # Add some space | |
| # Display each article as a clean clickable card | |
| for i, html_file in enumerate(html_files): | |
| # Extract filename without path and extension, format it nicely | |
| file_name = os.path.splitext(os.path.basename(html_file))[0] | |
| display_name = file_name.replace('_', ' ').replace('-', ' ').title() | |
| # Get file size | |
| try: | |
| file_size = os.path.getsize(html_file) | |
| size_kb = round(file_size / 1024, 1) | |
| size_text = f"{size_kb} KB" | |
| except: | |
| size_text = "- KB" | |
| # Create a clean card-like button | |
| article_clicked = st.button( | |
| f"📄 {display_name} ({size_text})", | |
| key=f"article_{i}", | |
| use_container_width=True | |
| ) | |
| if article_clicked: | |
| try: | |
| with open(html_file, 'r', encoding='utf-8') as file: | |
| html_content = file.read() | |
| # Display article content inline | |
| st.markdown("---") | |
| st.markdown(f"### {display_name}") | |
| # Add download option | |
| col1, col2 = st.columns([1, 4]) | |
| with col1: | |
| st.download_button( | |
| label="⬇️ Download", | |
| data=html_content, | |
| file_name=os.path.basename(html_file), | |
| mime="text/html", | |
| key=f"download_clicked_{i}" | |
| ) | |
| with col2: | |
| if st.button("❌ Close Article", key=f"close_{i}"): | |
| st.rerun() | |
| # Display the HTML content | |
| st.components.v1.html(html_content, height=600, scrolling=True) | |
| except Exception as e: | |
| st.error(f"Error loading article: {str(e)}") | |
| # Add small spacing between articles | |
| st.markdown("") | |
| def display_apps(): | |
| st.markdown('## Apps') | |
| st.markdown(""" | |
| - [CNN arch](https://cnn-arch.streamlit.app/) | |
| """) | |
| st.markdown(""" | |
| - [TuNNe](https://huggingface.co/spaces/Niharmahesh/TuNNe) | |
| """) | |
| def display_certifications(): | |
| st.markdown('## Certifications') | |
| certifications = [ | |
| {"title": "Python for Data Science and Machine Learning Bootcamp", "issuer": "Udemy", "date": "2023", "skills": "Python, Data Science, Machine Learning"}, | |
| {"title": "HackerRank SQL (Basic)", "issuer": "HackerRank", "date": "2023", "skills": "SQL, Database Management"}, | |
| {"title": "AWS Cloud Practitioner", "issuer": "Udemy", "date": "2023", "skills": "Cloud Computing, AWS Services"}, | |
| {"title": "AWS Certified Cloud Practitioner", "issuer": "Amazon Web Services", "date": "2023", "skills": "Cloud Architecture, AWS Best Practices"} | |
| ] | |
| for cert in certifications: | |
| with st.expander(cert["title"]): | |
| st.write(f"**Issuer:** {cert['issuer']}") | |
| st.write(f"**Date:** {cert['date']}") | |
| st.write(f"**Skills:** {cert['skills']}") | |
| def display_social_media(): | |
| st.markdown('## Social Media') | |
| st.markdown(""" | |
| - [LinkedIn](https://www.linkedin.com/in/sai-nihar-1b955a183/) | |
| - [GitHub](https://github.com/niharpalem) | |
| - [Medium](https://medium.com/@nihar-palem) | |
| - [Twitter](https://twitter.com/niharpalem_2497) | |
| - [Email](mailto:sainiharreddy.palem@sjsu.edu) | |
| """) | |
| # Updated menu with articles section | |
| menu_items_with_icons = { | |
| "🎓": display_education, | |
| "💼": display_work_experience, | |
| "📁": display_projects, | |
| "🛠️": display_skills, | |
| "📝": display_articles, # New articles section | |
| "🌐": display_social_media, | |
| "🏆": display_certifications, | |
| "📱": display_apps | |
| } | |
| def main(): | |
| # Initialize session state for selected function | |
| if 'selected_function' not in st.session_state: | |
| st.session_state.selected_function = None # Default to None to not display any section initially | |
| # Display the header with your name and Lottie animation first | |
| display_header() | |
| # Display the summary section immediately after the header | |
| display_summary() | |
| # Create a row of buttons for each icon in the menu | |
| cols = st.columns(len(menu_items_with_icons)) | |
| for col, (icon, func) in zip(cols, menu_items_with_icons.items()): | |
| if col.button(icon): | |
| # Update the session state to the selected function | |
| st.session_state.selected_function = func | |
| # If a function has been selected, call it | |
| if st.session_state.selected_function is not None: | |
| st.session_state.selected_function() | |
| if __name__ == "__main__": | |
| main() |