6 days ago
Remote, Mexico or Monterrey, MexicoSenior
Responsibilities
- Build and ship features across Champion platform repositories.
- Improve developer experience through tooling, scaffolding, documentation, and onboarding paths.
- Maintain and evolve the MCP tool server and agent infrastructure.
- Support business-unit Applied AI engineers with Champion development, deployment, and operations.
- Review agent implementations for prompt quality, scope enforcement, authentication configuration, and deployment setup.
- Pair with business-unit engineers on Kubernetes manifests, database registration, and LaunchDarkly prompt rollouts.
- Design and build Champion agents for business-unit use cases.
- Write and iterate on system prompts, tool bindings, and context injection for production agents.
- Register agents in Champion Server and configure environment-gated prompt rollouts.
- Write tests before implementation and follow trunk-based development, small pull requests, feature flags, conventional commits, and backward-compatible API and schema changes.
Requirements
- Proficiency in async Python, Pydantic, type hints, and FastAPI.
- Experience with the Strands agent SDK or a comparable agentic framework.
- Comfort with pytest, pytest-asyncio, and DeepEval for agent-specific evaluation.
- Ability to write and iterate on production XML-structured, scope-enforced system prompts and tool descriptions.
- Hands-on experience building or consuming Model Context Protocol servers.
- Familiarity with multi-agent architectures, orchestration, delegation, parallel tool use, handoffs, and cross-agent context management.
- Ability to design and run agent evaluation suites covering correctness, scope enforcement, regressions, and prompt iteration.
- Comfort authoring Dockerfiles, multi-stage builds, and local development environments with docker-compose and make.
- Comfort with templated PostgreSQL INSERT/SELECT queries, foreign-key relationships, and ER diagrams.
- Ability to follow conventional commit formats and pull-request-based trunk workflows.
- Working knowledge of Kubernetes Deployments, Services, ConfigMaps, ServiceAccounts, manifests, and kubectl is a plus.
- Working knowledge of AWS ECR, EKS, IAM, and Bedrock is a plus.
- Conceptual understanding of OAuth2/OIDC Authorization Code Flow with PKCE, token exchange, and agent authentication delegation is a plus.
- Beginner-level Terraform familiarity is a plus.
- LaunchDarkly experience is a plus.
- AWS Textract or comparable document intelligence and OCR pipeline experience is a plus.
- Comfort using Claude Code and Cursor throughout planning, implementation, review, and documentation, and evaluating AI-generated output critically.
- Work authorization in Mexico is required.
Benefits
- Fully remote work arrangement based in Mexico.
- Visa sponsorship is not offered.
- Opportunity to work on ChampionAI, an agentic platform for manufacturing and supply-chain use cases.
- Inclusive workplace committed to diversity, equity, and inclusion.
