AI Engineer (RAG & Agentic Applications)

AI Engineer

Responsibilities:

• Design and build scalable RAG pipelines

  , integrating

  embedding models

  ,

  vector databases

  , and

  LLM inference layers

  for

  high-accuracy, low-latency applications

  .

• Develop and deploy autonomous, multi-step AI agents and workflows

  using frameworks like

  LangChain, LangGraph, AutoGen

  , etc., to solve complex problems across

  text, document, audio, and video domains

  .

• Maintain ML applications

  by managing

  CI/CD deployment (Kubernetes)

  , monitoring performance, and iterating on production models using

  log analysis

  and

  stakeholder feedback

  .

• Prototype cutting-edge LLM and Transformer-based models

  for

  structured and unstructured data

  .

• Lead and mentor

  by conducting

  technical reviews of AI models

  , establishing best practices, and optimizing team output.

• Collaborate with product managers, developers, and customers

  to innovate and integrate

  scalable AI solutions

  .

Required Skills & Experience:

• 46 years of experience

  in

  artificial intelligence / machine learning

  , with

  successful industry-grade AI solution deployments

  .
• Minimum

  1+ years of hands-on experience

  in building

  Agentic AI applications

  .
• Strong programming expertise in

  Python

  and libraries such as

  PyTorch, TensorFlow, Hugging Face, Scikit-learn

  .
• Experience with

  LLM APIs

  (OpenAI, Claude, Gemini, etc.) and

  agentic frameworks

  (LangChain, LangGraph, AutoGen, AgentBuilder).
• Strong knowledge of

  vector databases

  (Pinecone, Chroma, Milvus, Elasticsearch) and

  API integration/orchestration tools

  .
• Hands-on experience with

  CI/CD deployment, monitoring, log analysis

  , and preferably

  Kubernetes

  .
• Exposure to

  cloud platforms

  (AWS, GCP, Azure) is an added advantage.