Description

Design and implement end-to-end generative AI solutions and agentic workflows.

This role is hybrid.

Responsibilities

• Design and implement RAG pipelines, including data ingestion, indexing, and retrieval strategies.
• Architect Agentic AI workflows and orchestration frameworks to manage autonomous agents.
• Optimize RAG systems for performance, accuracy, and latency.
• Conduct research and experimentation with LLM technology to drive best practices.
• Collaborate with data scientists, engineers, and product managers on technical implementation.

Required Skills

• 5+ years of experience in relevant technical roles.
• Deep understanding of Large Language Models (LLMs) and RAG pipeline development.
• Proficiency in Python and libraries including NumPy and Pandas.
• Expertise in LangChain and LangGraph.
• Experience with AutoGen and agentic orchestration.
• Familiarity with vector databases such as Pinecone, Weaviate, or Chroma.
• Strong knowledge of NLP techniques and prompt engineering.
• Practical experience with cloud platforms including AWS, Azure, or GCP.
• Solid grasp of machine learning, deep learning, and software development best practices.

Preferred Skills

• Experience with Scikit-learn for machine learning workflows.

Key Skills

Education

Any Gradute