Software Engineer, AI Agent Platform

Overview

Software Engineer for the AI Agent Platform (ChampionAI) joining a core platform team to build platform capabilities, enable partner Applied AI teams, and develop Champion agents for business-unit use cases.

What you'll do

• Build and ship features across Champion platform repositories.
• Improve developer experience via tooling, scaffolding, internal documentation, and onboarding paths.
• Maintain and evolve the MCP tool server and agent infrastructure used by business units.
• Support Applied AI engineers in building, deploying, and operating Champions correctly.
• Review agent implementations for prompt quality, scope enforcement, auth configuration, and deployment setup.
• Design and build Champion agents for business-unit use cases when the platform team is directly engaged.
• Write and iterate on system prompts, tool bindings, and context injection for production agents.

What you'll need

• Proficiency in async Python, Pydantic, type hints, and FastAPI.
• Experience with the Strands agent SDK or a comparable agentic framework.
• Strong testing skills using pytest, pytest-asyncio, and DeepEval for agent-specific evaluation.
• Ability to write and iterate on production system prompts (XML-structured, scope-enforced, tool descriptions for reliable LLM delegation).
• Solid understanding of MCP with hands-on experience building or consuming MCP servers.
• Familiarity with multi-agent architectures and orchestration patterns beyond basic ReAct.
• Comfortable with Docker (Dockerfiles, multi-stage builds, local dev via docker-compose/make).

Details

• Location: Monterrey, N.L., Mexico.