Generative AI Engineer with 2+ years of hands-on experience designing, developing, and deploying production-grade GenAI solutions using Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) pipelines. Expert in building scalable AI-powered backend services with strong expertise in Python, FastAPI, Google Cloud Platform (Vertex AI), vector databases, and agentic workflows. Proven track record of delivering enterprise-grade AI applications with focus on performance optimization, observability, and security.

• LLM Integration: Claude, Gemini, OpenAI API
• RAG Pipelines: Embedding models, document chunking, indexing, retrieval optimization
• AI Frameworks: LangChain, LlamaIndex, Hugging Face Transformers , Crewai , Agno
• Agentic Systems: Multi-agent workflows, tool integration, autonomous reasoning
• Prompt Engineering: Chain-of-thought, few-shot learning, output optimization

• Backend Development: Python, FastAPI, Django REST Framework, Flask
• APIs & Integration: REST APIs, Webhooks, OAuth2, JWT, Microservices
• Cloud Platforms: Google Cloud (Vertex AI, Cloud Run, Cloud Storage), AWS
• Databases: PostgreSQL, MySQL, MongoDB , CasandraDB , Redis
• Vector Databases: FAISS, Chroma, Pinecone, OpenSearch

• Observability: Logging, monitoring, evaluation metrics (RAGAS)
• Performance: Latency optimization, caching, batch processing, cost reduction
• Security: Enterprise security, data governance, HIPAA compliance, IAM
• Deployment: Docker, Kubernetes, CI/CD, Cloud Run, serverless

Nuvae.ai | Aug 2025 – Feb 2026 | Remote

• Designed and deployed production-grade GenAI solutions using GPT-4, Claude, and Gemini for healthcare automation workflows
• Built end-to-end RAG pipelines with advanced embedding models, document chunking strategies, and optimized retrieval techniques
• Deployed scalable applications on GCP using Vertex AI, Cloud Run, and Cloud Storage with 50,000+ daily requests at sub-200ms latency
• Integrated vector databases (FAISS, Chroma) with hybrid retrieval, improving search accuracy by 35% and query performance by 50%
• Implemented LangChain/LlamaIndex frameworks for agent-based workflows, tool integration, and multi-step reasoning systems
• Established ML evaluation metrics (RAGAS) for retrieval accuracy, response quality, and hallucination detection
• Applied prompt engineering techniques including chain-of-thought reasoning and systematic output optimization
• Optimized cloud costs by 40% through efficient model selection, caching strategies, and batch processing
• Implemented enterprise security and data governance with IAM policies, encryption, and privacy-compliant data handling

AOT Technologies | Feb 2024 – Aug 2025 | Thiruvananthapuram, India

• Developed RAG pipelines for document intelligence platforms with embedding models, chunking algorithms, and semantic retrieval
• Built LLM-based applications using OpenAI and Gemini APIs serving 10,000+ daily users in production
• Integrated vector databases (FAISS, Chroma) with efficient indexing and retrieval for large-scale document collections
• Created scalable GenAI APIs using FastAPI with authentication, rate limiting, and comprehensive error handling
• Implemented prompt engineering strategies reducing hallucinations by 40% and improving response consistency
• Applied performance optimization including model quantization, caching, and async processing
• Established ML observability with logging, monitoring, and alerting ensuring high availability
• Worked with GCP services including Cloud Storage, Cloud Functions, and serverless processing

Tech: Python, LangChain, Vertex AI, Cloud Run, FAISS, FastAPI

• Architected comprehensive RAG pipeline on GCP with Vertex AI for LLM serving and Cloud Storage for document management
• Implemented advanced chunking strategies (recursive, semantic) and embedding models (text-embedding-ada-002, GCP embeddings)
• Built vector database integration with FAISS and Chroma using hybrid retrieval (semantic + keyword matching)
• Developed scalable API deployment on Cloud Run with auto-scaling, load balancing, and IAM-based security
• Applied prompt engineering with context optimization and evaluation using RAGAS metrics
• Integrated LangChain for agent orchestration, tool calling, and multi-step reasoning with memory management
• Achieved 45% cost reduction through batch processing, caching strategies, and optimized model selection

Tech: LangChain, Vertex AI, Cloud Functions, Pinecone, FastAPI

• Developed GenAI application using Vertex AI for model deployment and Cloud Functions for event-driven processing
• Built RAG system with Pinecone vector database and advanced retrieval techniques for medical data
• Created LangChain-based agents with tool integration enabling autonomous decision-making workflows
• Implemented performance optimization achieving sub-500ms response times
• Established HIPAA-compliant data governance ensuring privacy and secure handling of healthcare information

Tech: Python, FastAPI, LLMs, REST APIs

• Developed backend service orchestrating multi-step eligibility and pre-auth workflows using AI-assisted decision logic
• Integrated multiple LLM providers with proper authentication, rate limiting, and fallback strategies
• Focused on correctness, validation, and observability in production healthcare environments

Amity University | 2024 – 2027
B.Sc. — Data Analysis

Central Polytechnic College | 2021 – 2024
Diploma — Computer Engineering

• LangGraph for Agentic Workflows — Advanced AI agent development with state management
• Practical Multi-Agent Systems (CrewAI) — Building collaborative AI workflows
• Develop GenAI Apps with Gemini — Google Cloud Vertex AI and Gemini integration
• Google Cloud Platform — Vertex AI, Cloud Run, Cloud Storage, IAM
• Data Science with Python — ML evaluation and performance optimization

Building GenAI solutions? Let's collaborate on RAG pipelines, agentic workflows, or LLM applications.