Praveen Sanpada

About Praveen Sanpada

Senior AI Systems Architect | IIT Patna M.Tech (AI & Data Science)| 4+ Years ExperienceI specialize in bridging the gap between cutting-edge AI research and production-grade engineering. With a focus on Generative AI, RAG architectures, and high-concurrency backends, I build distributed systems that don’t just work — they scale.Currently pursuing my M.Tech in AI & Data Science at IIT Patna (8.93 CGPA), I combine academic rigor with over 4 years of hands-on industry experience in architecting scalable microservices and AI-driven platforms.Core Expertise• Generative AI & LLMs: Production-grade RAG pipelines, Prompt Engineering, Fine-tuning, and Agentic workflows using LangChain, OpenAI, and SBERT.• High-Performance Backend: Architecting low-latency microservices using FastAPI, Node.js, and Python, consistently reducing API latency by 25–30%.• Data & Vector Engineering: Semantic retrieval and indexing using FAISS, Qdrant, PostgreSQL, and MongoDB.• Cloud-Native Deployments: Scaling AI workloads on AWS (EC2, Lambda, S3) using Docker and Kubernetes for high-availability systems.Key Impacts• Built a Private GPT system enabling sub-second semantic search across massive document sets using RAG and Vector Databases.• Architected AI-driven microservices supporting 10K+ monthly active users with 99.9% uptime.• Reduced manual intervention by 50% through intelligent backend workflow automation.Interests & FocusAI-Ops | System Design | Autonomous Agents | Scalable AI InfrastructureTech StackPython | FastAPI | Node.js | LLMs | RAG | AWS | Docker | React.js | Vector SearchOpen To OpportunitiesSenior AI EngineerBackend ArchitectLead AI DeveloperTarget Companies: Tier-1 Product MNCs & High-Frequency Trading (HFT) Firms

Experience

1. Senior Software Engineer Ai & Genai Systems

   Vinfotech

   May 2024 — Present · Indore, IN

   At Vinfotech, I design and build scalable backend systems and AI-powered applications, focusing on performance, reliability, and intelligent data retrieval.• Developed high-performance backend services using Python and FastAPI to support scalable microservices architecture.• Built Retrieval-Augmented Generation (RAG) pipelines integrating Large Language Models (LLMs) to power contextual Q&A systems, improving AI retrieval speed by 60%.• Integrated OpenAI and Hugging Face models with advanced prompt engineering techniques for domain-specific AI applications.• Implemented vector search solutions using FAISS and Qdrant for semantic search and intelligent document retrieval.• Reduced API latency by 25% through query optimization, async processing, and efficient caching strategies.• Deployed ML models and backend services on AWS (EC2, S3, Lambda), ensuring scalability and high availability.• Containerized applications using Docker and implemented CI/CD pipelines for streamlined deployments.• Collaborated with cross-functional teams in Agile sprints to deliver AI-driven features to production.Tech Stack: Python, FastAPI, RAG, LLM Integration, FAISS, Qdrant, PostgreSQL, MongoDB, AWS, Docker, Microservices, REST APIs, Git

Education

• Indian Institute of Technology, Patna

  Master of Technology (M.Tech), Artificial Intelligence & Data Science

• Poornima University

  Bachelor of Technology (B.Tech), Computer Science Engineering