Role Overview

Hiring AI engineers to build and deploy generative‑AI powered products using multi‑LLM architectures, RAG systems, vector databases, LLMOps, agents, and orchestration frameworks.

Key Responsibilities

• Build scalable RAG pipelines

• Develop agentic workflows using LangChain / LlamaIndex

• Train/fine‑tune LLMs (open-source or proprietary)

• Build vector DB indexing & retrieval layers

• Implement observability & LLMOps

Required Technical Skills

• Vector DBs (Pinecone, Weaviate, Milvus, FAISS)

• LangChain, LlamaIndex, OpenAI APIs

• Python, FastAPI, microservices

• Prompt engineering & evaluation

• Knowledge of embeddings, transformers