2 months 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.
Tech Stack
Categories
About QAD, Inc.
QAD builds cloud-based ERP and supply chain software for manufacturing companies, with offerings like QAD Adaptive ERP and the Redzone Connected Workforce platform, sold primarily by subscription with professional services. Its products target mid-market firms across automotive, industrial, food & beverage, life sciences, and consumer goods, embedding workflow and shop-floor capabilities. Founded in 1979 and headquartered in Miami, QAD is privately held and owned by Thoma Bravo.