AI / ML Lead - LLM / RAG

Role Summary :

We are building GenAI-driven assistants to transform how professionals learn, buy, and get support. You'll work closely with the CTO and lead the architecture, development, and deployment of LLM-powered solutions-including custom model training on proprietary datasets, RAG pipelines, and multi-agent systems.

This is a full-stack AI role-you'll also drive infrastructure, DevOps, and observability across the GenAI stack to ensure production-grade performance, scalability, and automation.

Must-Have Skills :

• LLM fine-tuning and custom model creation using proprietary data (e.g., SFT, LoRA, PEFT)
• Strong expertise in RAG architectures, vector stores (Pinecone, FAISS), and embeddings
• Hands-on with LangChain, LangGraph, and prompt engineering
• Solid cloud experience (AWS - ECS, Lambda, Bedrock, S3, IAM)
• Backend / API engineering (FastAPI or Node.js), Docker, Git, CI / CD (GitHub Actions, CodePipeline)
• Scripting with Python & Bash; n8n or other workflow automation tools
• Observability : Langfuse, LangWatch, OpenTelemetry

Bonus Skills :

You'll Be Responsible For :

(ref : hirist.tech)