Software Engineer, AI Agent Platform
RemoteMexico
Job Summary
Build and ship features across the Champion platform repositories while improving developer experience through tooling, scaffolding, and onboarding paths. Maintain the MCP tool server and agent infrastructure that business units depend on, identifying friction points that slow deployment. Support Applied AI engineers by reviewing agent implementations for prompt quality, auth configuration, and deployment setup, then pair with them on K8s manifests and LaunchDarkly rollouts. Design and build Champion agents for specific use cases, writing system prompts and iterating on tool bindings for production environments. Write tests before implementing using TDD, keeping PRs small and focused with feature flags to ship partial work incrementally.
Required Qualifications
- Proficient in async Python, Pydantic, type hints, and FastAPI
- Experience with the Strands agent SDK or a comparable agentic framework
- Testing is non-optional: candidates should be comfortable with pytest, pytest-asyncio, and DeepEval for agent-specific evaluation
- Able to write and iterate on production system prompts: XML-structured, scope-enforced, with tool descriptions that guide LLM delegation reliably
- Solid understanding of MCP and hands-on experience building or consuming MCP servers
- Familiarity with Agent-to-Agent (A2A) protocol
- Familiar with multi-agent architectures and orchestration patterns beyond basic ReAct: supervisor/subagent delegation, parallel tool use, handoffs, and context management across agent boundaries
- Able to design and run evaluation suites for agent behavior: correctness checks, scope enforcement tests, regression coverage, and systematic prompt iteration based on eval results
- Comfortable authoring Dockerfiles, multi-stage builds, and local dev environments via docker-compose / make
- Comfortable with templated INSERT/SELECT, foreign key relationships, and reading an ER diagram
- Follows conventional commit format (feat:, fix:) and a PR-based trunk workflow
- Use Claude Code and Cursor actively across planning, implementation, and code review
- Know when AI output is wrong and push back on it
- Help drive adoption across the team by sharing what works
- This is not an ML research or data science role
Desired Qualifications
- A2A protocol is a strong plus
- Working knowledge of Kubernetes: Deployments, Services, ConfigMaps, and ServiceAccounts
- Able to read and adapt K8s manifests and use kubectl for basic troubleshooting
- Working knowledge of AWS: ECR, EKS, IAM, and Bedrock (inference layer)
- Conceptual understanding of Authorization Code Flow with PKCE, token exchange, and agent auth delegation
- Beginner-level familiarity with Terraform; able to make targeted changes to existing modules and interpret a plan diff
- Experience managing feature flags or AI config overrides for environment-gated rollout
- AWS Textract or comparable pipeline experience for use cases involving structured document extraction
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.