Description

You will design, build, and deploy complex LLM-powered applications, including RAG systems and intelligent agents.

This role is hybrid.

Responsibilities

• Design LLM applications focusing on tasks, context, tools, and feedback loops.
• Build and refine Retrieval Augmented Generation (RAG) systems with quality chunking, retrieval, and citation logic.
• Orchestrate agents by implementing planning, decomposition, tool-calling, and memory stores.
• Deploy solutions into production while managing monitoring, evaluation, and cost.

Required Skills

• 4-8+ years in software or ML engineering.
• 1-3+ years experience with LLM, agent, or RAG systems.
• Strong proficiency in Python or TypeScript, including async programming and API design.
• Hands-on experience with OpenAI/Azure OpenAI (Assistants API, GPT-4.1+/o-series) and embeddings.
• Practical expertise building RAG using a vector DB and retrieval strategy beyond basic semantic search.
• Experience with agent frameworks such as LangGraph, AutoGen, CrewAI, or OpenAI Assistants with tools.
• Familiarity with prompt engineering, tool/function calling, schema design, and context windows.
• Proven production deployment experience with observability and cost management.

Key Skills

Education

Any Gradute