Open to opportunities

Ansh Mangukiya

@anshmangukiya

Message

AI Engineer building production Generative AI systems with RAG and agents.

India

Message

What I'm looking for

I’m looking for an AI engineering role where I can ship production LLM/RAG and multi-agent systems, optimize multi-GPU inference, and integrate GenAI into real enterprise workflows with strong engineering ownership.

I’m an AI Engineer with 1.5+ year of hands-on experience designing and deploying production-grade Generative AI systems—RAG pipelines, fine-tuned LLMs, and multi-agent orchestration platforms.

I focus on practical performance and reliability: I built a custom multi-GPU LLM inference stack on vLLM with batching, KV-cache optimization, and parameter tuning, achieving 150+ tokens/second throughput under concurrent load.

My work has translated into measurable business impact—80% reduction in customer onboarding time, a 60% drop in manual ticket triage effort, and 60–70% less manual engineering effort across automation initiatives.

I also value real-world integration. I bridge enterprise systems by connecting .NET applications (ASP.NET/C#) with Python AI services via FastAPI microservices and REST contracts, enabling context-aware chatbot experiences through RAG, semantic search, and agent workflows using LangGraph/LangChain.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Commercient LLC

Jan 2025 - Present (1 year 5 months)

Architected and deployed an ingestion and chatbot platform for autonomous enterprise GenAI assistant launches, cutting manual ticket triage effort by 60% and improving response consistency. Built vLLM-based multi-GPU inference (150+ tokens/sec), RAG pipelines, multi-agent orchestration for ERP-to-CRM sync, and FastAPI/.NET integration to reduce engineering support load by 70%.

VLLM Retrieval Augmented Generation (RAG)LangGraph Pinecone ChromaDB FAISS fastAPI .NET (C# ASP.NET) Integration