AI / ML Engineer

Responsibilities:
Build agentic pipelines using LangChain, LangGraph, and MCP/tool-use frameworks.
Create vector retrieval systems with Pinecone, Milvus, FAISS, and Weaviate.
Develop model inference, evaluation, and data processing pipelines.
Implement embedding workflows, prompt templates, and structured output validation.
Integrate AI components into platform APIs (Python/FastAPI).
Requirements:
5-10 years in ML engineering or platform-oriented AI development.
Strong Python and PyTorch.
Hands-on with RAG, embeddings, LLMs, and vector DBs.
Experience with Kubernetes/AWS/Azure or model deployment pipelines is a plus.

Experience
6-10 yrs