Description

Build the backend infrastructure, tooling, and orchestration logic that powers autonomous AI agents, ensuring secure, scalable, and efficient execution of complex reasoning tasks.

This role is on-site.

Responsibilities

• Develop and maintain backend tools (APIs, scrapers, database connectors) that AI agents use to perform tasks.
• Implement complex reasoning chains and multi-agent coordination using frameworks like LangChain, LangGraph, or CrewAI.
• Build and optimize data ingestion and retrieval systems using Vector Databases to ensure agents have the right context.
• Manage long-running AI reasoning cycles using asynchronous Python (FastAPI/Asyncio) and task queues like Celery or Redis.
• Design secure, high-performance REST or GraphQL APIs and implement backend-level validation and guardrails for agent actions.

Required Skills

• 8+ years of professional experience with Python, specifically FastAPI, Pydantic, and Asyncio.
• Hands-on experience with LangChain, LangGraph, or CrewAI for agent orchestration.
• Proficiency in PostgreSQL and experience with Vector Databases.
• Experience deploying containerized applications using Docker and Kubernetes on AWS, Azure, or GCP.
• Understanding of distributed systems to handle high latency and compute requirements of LLM-based applications.
• Mastery of Git and CI/CD best practices.

Preferred Skills

• Knowledge of Prompt Engineering from a programmatic perspective, including dynamic prompt templating.
• Familiarity with AI observability tools such as LangSmith or Arize Phoenix.

Key Skills

Education

Any Graduate