Description

What You’ll Work On:
- Build LLM apps (RAG, multi-agent, automation)
- Optimize latency, cost, and inference performance
- Design eval pipelines and prompt strategies
- Collaborate with platform & backend teams

Required Skills:
- Strong Python, LLM ecosystems, prompt engineering
- LangChain, DSPy, or LangGraph
- Vector DBs (Pinecone, Weaviate, Milvus)
- Production AI deployment & experiment tracking
- Cloud (AWS/Azure/GCP), REST APIs, microservices

Preference:
- Agent frameworks, fine-tuning, ML observability
- Product-based company background
- Immediate joiners prioritized

Key Skills

Education

Any Graduate