Description

You will build and deploy production-grade LLM applications, agents, and RAG systems. This role is on-site.

Responsibilities

• Design and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases and advanced retrieval strategies beyond basic semantic search.
• Develop autonomous agent systems using frameworks like LangGraph or AutoGen, focusing on planning, tool-calling, and memory management.
• Integrate with OpenAI and Azure OpenAI APIs, managing context windows, token budgets, and structured outputs for reliable performance.
• Ensure production readiness by implementing monitoring, evaluation metrics, and cost management for AI-driven features.
• Write clean, tested Python code with a focus on async programming, API design, and distributed systems principles.

Required Skills

• 5+ years of software or ML engineering experience.
• 1-3+ years of hands-on experience with LLMs, agents, or RAG systems.
• Strong proficiency in Python or TypeScript, including async programming patterns.
• Practical experience building RAG solutions with at least one vector database.
• Experience with agent frameworks such as LangGraph, AutoGen, or CrewAI.
• Familiarity with prompt engineering, function calling, and schema design.
• Proven track record of deploying AI applications to production with observability.

Preferred Skills

• Experience with the Azure ecosystem (Azure AI Search, App Service, Key Vault).
• Knowledge of data privacy, security, and PII redaction techniques.

Key Skills

Education

Any Graduate