Posted on: 27/08/2025
About Us :
We are a fast-growing B2B SaaS company building cutting-edge Generative AI and LLM-powered platforms that help enterprises scale decision-making, automation, and intelligent insights.
What Youll Do :
- Build and deploy agentic LLM solutions with LangGraph, LangChain, DSPy, and other modern frameworks
- Architect RAG pipelines, multi-turn conversational agents, and document automation systems
- Work on observability & evaluation of LLMs using tools like Langfuse, Langsmith, and DSPy evals
- Optimize inference pipelines with Ray, FastAPI, and distributed systems
- Collaborate with product & infra teams to take GenAI products from R&D to production
What Were Looking For :
- Strong experience in Python (FastAPI/Django preferred)
- Hands-on with LLM frameworks (LangChain, LangGraph, DSPy, Mem0, LightRAG, etc.)
- Knowledge of vector databases (Milvus, Pinecone, FAISS) and retrieval mechanisms
- Understanding of transformers, tokenization, embeddings and how to evaluate LLM performance (BLEU, ROUGE, retrieval hit-rate)
- Exposure to MLOps, distributed computing (Ray/Kubernetes) is a plus
- Education from Tier-1/Tier-2 engineering institutes preferred
Why Join Us ?
- Work at the forefront of GenAI + Agentic systems
- Be part of a high-growth SaaS startup solving real enterprise problems
- Opportunity to work with top-tier engineers and researchers
- Fast-paced environment with ownership and growth trajectory
Did you find something suspicious?