2 months ago
Remote, Mexico or Monterrey, MexicoSenior
Responsibilities
- Build and ship features across Champion platform repositories.
- Improve developer experience through tooling, scaffolding, internal documentation, and onboarding paths.
- Maintain and evolve the MCP tool server and agent infrastructure.
- Support Applied AI engineers with building, deploying, and operating Champions.
- Review agent implementations for prompt quality, scope enforcement, authentication configuration, and deployment setup.
- Create internal engineering guides and pair with business-unit engineers on Kubernetes manifests, database registration, and LaunchDarkly prompt rollouts.
- Design and build Champion agents, including system prompts, tool bindings, context injection, and environment-gated prompt configuration.
- Develop agent evaluation suites covering correctness, scope enforcement, regression coverage, and prompt iteration.
- Follow trunk-based development, PR-gated merges, test-first development, small focused pull requests, feature flags, conventional commits, and backward-compatible API and schema changes.
- Use Claude Code and Cursor throughout planning, implementation, review, and documentation while evaluating and improving AI-generated output.
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 testing and evaluating agent behavior.
- 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, including supervisor/subagent delegation, parallel tool use, handoffs, and cross-agent context management.
- Ability to design and run agent behavior evaluation suites.
- Comfort authoring Dockerfiles, multi-stage builds, and local environments using docker-compose and make.
- Working knowledge of PostgreSQL templated INSERT/SELECT queries, foreign-key relationships, and ER diagrams.
- Familiarity with Git, conventional commits, pull-request workflows, and semantic versioning.
- Kubernetes knowledge involving Deployments, Services, ConfigMaps, ServiceAccounts, kubectl, and manifest adaptation is preferred.
- AWS experience with ECR, EKS, IAM, and Bedrock is preferred.
- OAuth2/OIDC knowledge, including Authorization Code Flow with PKCE, token exchange, and agent authentication delegation, is preferred.
- Beginner Terraform familiarity, including targeted module changes and plan-diff interpretation, is preferred.
- LaunchDarkly experience is preferred.
- AWS Textract or comparable document-intelligence/OCR pipeline experience is preferred.
- Comfort with AI-assisted development using Claude Code and Cursor is required.
Benefits
- Fully remote work based in Mexico.
- The company states that it values employee contributions, diverse perspectives, inclusion, and opportunities for growth.
- Equal Opportunity Employer committed to non-discrimination across protected characteristics.
- Visa sponsorship is not offered.
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.