Senior ML Engineer / Applied Scientist – RAG, Agentic Systems, vLLM / SG Lang & Vector Databases (Product Team)

We’re building next-gen AI-powered product experiences — intelligent assistants, agentic workflows, and scalable RAG systems. We’re hiring a Senior ML Engineer / Applied Scientist who can build production-grade RAG architectures , develop agentic systems (LangGraph, CrewAI, AutoGen), and deploy high-performance LLM inference using vLLM, SGLang, TensorRT-LLM , while working with modern vector databases (Qdrant, MongoDB Vector Search) .

This is a hands-on role at the intersection of AI systems, retrieval, agents, and product engineering.

What You’ll Do

• Build end-to-end RAG pipelines (ingestion → embeddings → vector DB → retrieval → generation).
• Work with open-source models (LLaMA, Mistral, Qwen, Gemma) and closed-source models (GPT-4.x, Claude 3, Gemini, Grok).
• Develop agentic workflows using LangGraph, CrewAI, AutoGen, LangChain, LlamaIndex .
• Deploy & optimize inference using vLLM, SGLang, TensorRT-LLM, TGI .
• Implement scalable vector search with Qdrant & MongoDB Atlas Vector Search .
• Build multilingual pipelines with Indic-language support.
• Set up evaluation using Ragas, DeepEval, LangSmith, TruLens .
• Work closely with backend / product teams to deploy RAG + agent systems in production.

What You Bring

Bonus Skills