Looking for a job

Bhaskar Anjappa

@bhaskaranjappa

“Generative AI Engineer building production RAG, multi-agent systems and LLM APIs. 3 years shipping with LangChain, Milvus, FastAPI.”

India

Message

What I'm looking for

GenAI engineer seeking to own production LLM systems end to end: retrieval, agent orchestration, serving and evaluation. I do my best work on RAG, multi-agent workflows and LLM APIs real users depend on. I prefer small to mid-sized teams with direct ownership, hard reliability problems and eval-driven quality. Remote-first. Open to contract RAG and agent work.

I’m a Generative AI Engineer at Aarya Tech Solutions (since July 2023), building production LLM systems end to end: retrieval, orchestration, serving and evaluation.

What I ship: RAG pipelines with hybrid search, CrossEncoder reranking and Milvus, which improved retrieval accuracy by 35% on proprietary datasets (measured on [your eval metric]). FastAPI services for LLM inference, agent workflows traced with LangSmith, and domain-specific prompting on Vertex AI and Gemini for summarization and classification. I also automate internal processes with n8n and Make.com.

Projects: a LangGraph multi-agent system for deep web research, an enterprise knowledge base chatbot with hybrid search (live demo linked below), and a GPT-style language model built from scratch in PyTorch and CUDA.

I’m open to GenAI engineering roles and freelance RAG/agent work.

Experience

Work history, roles, and key accomplishments

Current

Generative AI Engineer

Current

Aarya Tech Solutions

Jul 2023 - Present (3 years 3 months)

Engineered production RAG pipelines using LangChain and Milvus, improving retrieval accuracy by 35%. Developed and deployed 10+ Custom GPTs and Google Gems, and built high-performance RESTful APIs with FastAPI for LLM inference.