About the role
- Design and develop autonomous AI agents and multi-agent workflows.
- Build LLM-powered applications using prompt engineering, function calling, and structured outputs.
- Develop Retrieval-Augmented Generation (RAG) pipelines using enterprise knowledge bases.
- Build AI solutions for candidate matching, resume understanding, skills extraction, job understanding, and intelligent recommendations.
- Develop semantic search, embeddings, and knowledge graph-based solutions.
- Optimize AI models for accuracy, latency, scalability, and cost.
- Collaborate with Product and Engineering teams to deploy production-grade AI applications.
- Strong proficiency in Python.
- Experience with LLMs, Agentic AI, RAG, Prompt Engineering, NLP, and Embeddings.
- Hands-on experience with frameworks such as LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, or similar.
- Experience with vector databases like Pinecone, Weaviate, Milvus, Qdrant, or FAISS.
- Familiarity with FastAPI, REST APIs, Docker, Kubernetes, Git, and cloud platforms (AWS, Azure, or GCP).
- Experience deploying AI applications in production environments.
- Experience in HRTech, SaaS, or enterprise AI products.
- Exposure to knowledge graphs, MLOps, AI evaluation frameworks, and Responsible AI practices.
- Familiarity with MCP (Model Context Protocol) and modern AI orchestration frameworks is a plus.