Software Engineer, AI Agent Platform

AI Engineer - ChampionAI Platform Team

About Redzone

Redzone is the leading Connected Workforce Solution for manufacturers, focused on improving plant efficiency, coaching best practices, and empowering frontline workers. We combine strong leadership, extensive manufacturing experience, and an exceptional technology team to deliver innovative products that ensure smooth and efficient manufacturing operations. Our commitment is to the customer experience and providing solutions that yield great outcomes.

About ChampionAI

ChampionAI is the agentic platform for QAD | Redzone, specifically designed for manufacturing. It empowers various business units within QAD | Redzone by building new capabilities, assisting Applied AI teams, and developing Champion agents for specific use cases. This role operates within the core platform team, working on the same codebase as the Applied AI engineers, ensuring platform work addresses real-world problems.

Role Focus

As an AI Engineer on the core platform team, you will have three primary areas of focus:

1. Platform Development: Building and shipping features across the Champion platform repositories, improving developer experience, and maintaining the agent infrastructure.
2. Applied AI Enablement: Supporting business unit Applied AI engineers in building, deploying, and operating Champions, reviewing agent implementations, and contributing to documentation.
3. Agent Development: Designing and building Champion agents for business unit use cases, iterating on prompts, and registering agents.

Key Responsibilities

Platform Development

• Build and ship features across Champion platform repositories.
• Improve developer experience through tooling, scaffolding, documentation, and onboarding.
• Maintain and evolve the MCP tool server and agent infrastructure.
• Identify and address friction points in Champion development or deployment.

Applied AI Enablement

• Support BU Applied AI engineers in building, deploying, and operating Champions.
• Review agent implementations for prompt quality, scope, auth, and deployment.
• Contribute to internal engineering guides and skill documentation.
• Pair with BU engineers on initial K8S manifest creation, database registration, and prompt rollout.

Agent Development

• Design and build Champion agents for BU use cases.
• Write and iterate on system prompts, tool bindings, and context injection for production agents.
• Register agents in Champion Server and configure feature-flagged prompt rollouts.

Engineering Practices

We follow trunk-based development with PR-gated merges to main. Engineers are expected to:

• Write tests before implementing (TDD).
• Keep PRs small and focused; use feature flags for incremental shipping.
• Follow conventional commit format (feat:, fix:, etc.).
• Be mindful of API and schema backward-compatibility.
• Review own diff before requesting review.

Core Requirements

• Python: Proficient in async Python, Pydantic, type hints, FastAPI. Experience with Strands agent SDK or comparable framework. Strong experience with pytest, pytest-asyncio, and DeepEval for agent evaluation.
• Prompt Engineering: Ability to write and iterate on production system prompts (XML-structured, scope-enforced, with reliable tool descriptions).
• Model Context Protocol (MCP): Solid understanding and hands-on experience building or consuming MCP servers. Familiarity with Agent-to-Agent (A2A) protocol is a plus.
• Agent Patterns: Familiarity with multi-agent architectures and orchestration patterns (supervisor/subagent delegation, parallel tool use, handoffs, context management).
• Agent Evals: Ability to design and run evaluation suites for agent behavior (correctness, scope enforcement, regression coverage).
• Docker: Comfortable authoring Dockerfiles, multi-stage builds, and local dev environments via docker-compose/make.
• PostgreSQL: Comfortable with templated INSERT/SELECT, foreign key relationships, and ER diagrams.
• Git / Semantic Versioning: Follows conventional commit format and a PR-based trunk workflow.

Nice to Have

• Kubernetes: Working knowledge of Deployments, Services, ConfigMaps, ServiceAccounts; ability to read/adapt manifests and use kubectl.
• AWS: Working knowledge of ECR, EKS, IAM, Bedrock.
• OAuth2 / OIDC: Conceptual understanding of Authorization Code Flow, token exchange, agent auth delegation.
• Terraform: Beginner-level familiarity.
• LaunchDarkly: Experience managing feature flags or AI config overrides.
• Document Intelligence / OCR: AWS Textract or comparable pipeline experience.

AI-Native Development

We utilize an AI-native SDLC with AI-assisted tools (Claude Code, Cursor) for planning, implementation, review, and documentation. Candidates should be comfortable with AI-assisted development and willing to invest in becoming proficient.

What This Role Is Not

This is not an ML research or data science role. The focus is on building reliable software on top of existing infrastructure and enabling others to do the same.

About QAD | Redzone

QAD | Redzone redefines manufacturing and supply chains with an intelligent, adaptive platform connecting people, processes, and data into a single System of Action. Our three pillars—Redzone (frontline empowerment), Adaptive Applications (intelligent backbone), and Champion AI (Agentic AI)—help manufacturers achieve Champion Pace with measurable productivity, resilience, and growth. We are committed to an inclusive environment that values contributions and offers growth opportunities.