Hello, I'm

Saurabh Chauhan

I am pursuing my Master of Science in Computer Science at the University of Illinois Springfield (expected May 2026, GPA 3.8), building on my Bachelor of Engineering in Computer Engineering from Pune University. With over three years of hands-on experience in backend development and distributed systems, I have architected and delivered scalable, high-performance applications serving thousands of users with measurable impact on system reliability and performance.

Work Authorization: Authorized to work in the United States. Eligible for OPT (1 year) + STEM OPT (2 years).

About Me

Saurabh Chauhan - AI/ML Engineer & Software Engineer

AI/ML Engineer

I'm currently pursuing my M.S. in Computer Science at the University of Illinois, building on my B.E. in Computer Engineering from Pune University. With 3+ years of specialized experience in artificial intelligence and machine learning, I've successfully developed and deployed production-grade AI systems that have driven measurable business impact.

At the University of Illinois Springfield, I am developing an AI-powered admissions chatbot using the OpenAI API with custom Drupal integration, implementing features including streaming responses, rate limiting, and persistent session management. This chatbot handles 200+ FAQ queries with 90% accuracy, transforming campus engagement by providing instant, intelligent responses to prospective students.

My expertise spans the entire machine learning lifecycle from data preprocessing and feature engineering to model development, optimization, and production deployment. At Product Dossier Solutions (Kytes), I architected a production RAG system using LangChain, Mistral-7B, and FAISS that serves 10,000+ users across six enterprise clients with 95% query accuracy and sub-50ms retrieval latency. I have built AI inference APIs using gRPC integrated with Spring Boot microservices, handling 110,000+ daily requests with 99.5% uptime. I specialize in TensorFlow, PyTorch, LangChain, and deploying ML models on cloud platforms (AWS, GCP) to serve thousands of concurrent users.

Backend Engineer

I'm currently pursuing my M.S. in Computer Science at the University of Illinois, building on my B.E. in Computer Engineering from Pune University. With 3+ years of hands-on experience in backend development and distributed systems, I've architected and delivered scalable, high-performance applications serving thousands of users.

At the University of Illinois Springfield, I am developing production-ready web components using Drupal CMS, Twig templates, and Bootstrap, ensuring WCAG 2.1-AA accessibility compliance and responsive design across mobile and desktop platforms. I am building an OpenAI-powered chatbot backend with LangChain, implementing Redis session management and RESTful endpoints that handle 200+ queries with 90% accuracy.

I excel in building robust backend systems with Java Spring Boot, Django, and FastAPI, specializing in microservices architecture, gRPC, and RESTful APIs. At Product Dossier Solutions (Kytes), I built high-throughput distributed systems handling 110,000+ daily requests through Spring Boot microservices communicating via gRPC and REST, implementing load balancing, Redis caching, and asynchronous queues to reduce response time by 40%. I developed an automated deployment system that reduced deployment time by 67%, supporting 10+ daily deployments. At Dasha Krit Technology (D10X), I architected a multi-tenant SaaS platform from scratch using Django and PostgreSQL, designing custom authentication, FSM-based workflow management, and RESTful APIs supporting 10+ models deployed to GCP serving 10+ enterprise clients.

3+
Years Experience
10+
Projects
10+
Technologies

Technical Skills

🤖 AI/ML Frameworks

TensorFlow 2.16 PyTorch 2.6 LangChain 2.0 Scikit-learn OpenAI API RAG Hugging Face spaCy NLTK

💻 Programming Languages

Python 3.12+ (Advanced) R 3.6 SQL Java 11 C++

🌐 Web & Frameworks

FastAPI Flask Streamlit Django Streamlit

☁️ Cloud & Infrastructure

AWS (ECS, EKS, EC2, S3, Lambda, SageMaker, ) GCP Docker Kubernetes CI/CD (Jenkins, GitHub Actions)

🗄️ Database & Caching

PostgreSQL SQLAlchemy SQL Server 2019 Oracle Redis Vector Databases (FAISS, ChromaDB)

📊 Data Science & MLOps

Pandas NumPy Apache Airflow PySpark MLflow

Work Experience

April 2025 – Present

Website Intern

University of Illinois – College of Health, Science & Technology
  • AI Chatbot Development: Building an OpenAI-powered chatbot backend with LangChain, implementing Redis session management and token-limited API calls, handling 200+ FAQ queries with 90% accuracy for prospective student engagement.
  • Production Web Development: Developing WCAG 2.1-AA compliant web components using Drupal CMS, Twig templates, and Bootstrap, ensuring responsive design across mobile and desktop platforms.
  • Performance Optimization: Built sophisticated client-side filtering system for Faculty Directory using vanilla JavaScript with debounce patterns, achieving sub-150ms response times for 400+ profiles.
  • RESTful API Development: Building OpenAI chatbot backend with LangChain, implementing RESTful endpoints with Redis session management and rate limiting, processing 200+ queries with 90% accuracy and sub-200ms response time.
  • CMS Modernization: Developing production-ready web components using Drupal CMS, creating RESTful API endpoints and optimizing database queries to reduce server load, ensuring WCAG 2.1-AA accessibility compliance.
  • DevOps Automation: Streamlined local development environments using DDEV on WSL 2/Docker, writing custom Composer scripts that reduced developer setup time from hours to under 30 minutes.
2023 – 2024

Software Engineer (AI-ML)

Product Dossier Solutions Pvt. Ltd.
  • Production RAG System: Architected enterprise RAG system using LangChain, Mistral-7B, and FAISS, integrated with RASA chatbot to serve 10,000+ users across six enterprise clients with 95% query accuracy and sub-50ms retrieval latency.
  • Distributed ML Pipeline: Migrated legacy single-threaded Apache Airflow DAGs to distributed PySpark architecture, enabling parallel execution that reduced data processing time by 65% for enterprise project management platform.
  • ML Microservices: Built AI inference APIs using gRPC integrated with Spring Boot microservices, handling 110,000+ daily requests with intelligent caching and load balancing, achieving 99.5% uptime.
  • Vector Database Implementation: Implemented FAISS vector database for semantic document search, processing 200+ PDFs per client with optimized embedding generation and sub-50ms retrieval latency.
  • Microservices Architecture: Built high-throughput distributed systems handling 110,000+ daily requests through Spring Boot microservices communicating via gRPC and REST, implementing load balancing, Redis caching, and asynchronous queues to reduce response time by 40%.
  • Deployment Automation: Implemented automated deployment system for PSA platform using Obevo and Apache Freemarker, reducing deployment time by 67% and supporting 10+ daily deployments with 5+ monthly production releases.
  • API Gateway Integration: Integrated Apache APISIX gateway with JWT authentication, rate limiting (1000 req/min), and load balancing, reducing API latency by 40% and eliminating security vulnerabilities.
  • CI/CD Pipeline: Engineered Docker-based CI/CD pipeline with Jenkins, enabling 50+ monthly zero-downtime releases with 100% success rate.
2021 – 2023

Software Engineer

Dasha Kirt Technologies Pvt. Ltd. (D10X)
  • SaaS Architecture: Programmed a Django multi-tenant workflow application from scratch, contributing 70% to the core codebase and leading the system design.
  • Data Automation: Created automated data pipelines using Python and SQLAlchemy to ingest daily NIFTY 50 market data, providing clients with immediate access to historical datasets for strategy backtesting and paper trading.
  • Test Automation Framework: Developed comprehensive test automation framework with 100+ test cases using Robot Framework and Playwright, reducing QA cycle time by 60% through data-driven testing methodology.
  • SaaS Architecture: Programmed a Django multi-tenant workflow application from scratch, contributing 70% to the core codebase and leading the system design.
  • Database Engineering: integrated daily updates into the database via SQLAlchemy ORM, optimizing query performance for live data feeds.
  • Real-time Systems: Developed a Fintech product architecture integrating third-party APIs and WebSockets for real-time stock market data processing.
  • DevOps: Created shell scripts to automate software deployments and manage Linux server configurations.
  • Test Automation: Developed comprehensive test automation framework with 100+ test cases using Robot Framework and Playwright, ensuring full feature coverage and reducing regression testing time by 60%.

Featured Projects

🤟

ASL to Text Recognition

Problem: Real-time American Sign Language translation using computer vision and deep learning.

Solution:
Fine-tuned VideoMAE transformer on 239-class ASL dataset, improving accuracy from 62% to 82% (+32% improvement) through novel Universal Temporal Sub-sampling technique optimized for GPU-constrained training. Implemented AdamW optimizer and cosine learning rate decay for optimal convergence. Supports multi-sign prediction from long-form videos with temporal context awareness.

Python PyTorch VideoMAE Hugging Face Computer Vision
🧠

Neurofinity (AI-Powered Productivity Tool)

Problem: Note-taking and idea organization is challenging for neurodivergent individuals.

Solution:
Developed AI-powered mind map generator using OpenAI Whisper for speech-to-text transcription, Hugging Face Transformers for key phrase extraction, and Graphviz for automatic visualization. Reduced note-taking time by 80% while improving information retention through visual organization tailored for ADHD and autism.

Python OpenAI Whisper Transformers NLP Accessibility
🔬

Research Assistant (Multi-Agent AI System)

Problem: Standard RAG systems perform single-chain retrieval with no source credibility evaluation or confidence scoring, producing unreliable research outputs.

Solution:
Built a production-grade multi-agent research system using AutoGen where specialized agents divide the pipeline - one retrieves and searches sources, a second evaluates credibility and assigns confidence scores, and a third synthesizes structured outputs with executive summaries, consensus/disagreement analysis, and numbered citations. Deployed on Amazon EKS with two replicas per service, ALB ingress, and zero-downtime rolling deployments representing a complete MLOps workflow.

Python AutoGen LangChain Mistral-7B FastAPI React Docker AWS EKS

Get In Touch

📍

Location

Chicago, Illinois

📱

Phone

+1 (217) 862-4640