Software Engineer, AI Agent Platform

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and deploy features across the Champion platform repositories.

• Enhance the developer experience through tools, scaffolding, documentation, and onboarding processes.

• Maintain and advance the MCP tool server and agent infrastructure.

• Identify and resolve obstacles that hinder Champion development or deployment.

• Assist Applied AI engineers within business units in building, deploying, and operating Champions.

• Evaluate agent implementations for prompt quality, scope adherence, authentication configuration, and deployment setup.

• Contribute to internal engineering documentation and skill guides.

• Collaborate with business-unit engineers on K8S manifests, database registration, and LaunchDarkly prompt rollouts.

• Design and create Champion agents tailored to business-unit use cases.

• Draft and refine system prompts, tool bindings, and context injection.

• Register agents in the Champion Server and set up LaunchDarkly-gated prompt rollouts.

• Adhere to trunk-based development practices with PR-gated merges.

• Write tests prior to implementation and keep pull requests concise and focused.

• Utilize feature flags for incremental delivery while ensuring API/schema backward compatibility.

⛳️ Requirements

• Proficient in async Python, Pydantic, type hints, and FastAPI.

• Experience with the Strands agent SDK or a similar agentic framework.

• Comfortable using pytest, pytest-asyncio, and DeepEval.

• Capable of writing and refining production system prompts.

• Strong understanding of MCP with practical experience in building or consuming MCP servers.

• Familiar with multi-agent architectures and orchestration patterns.

• Able to design and execute evaluation suites for agent behavior.

• Proficient in authoring Dockerfiles, multi-stage builds, and managing docker-compose / make environments.

• Comfortable with templated PostgreSQL INSERT/SELECT, foreign key relationships, and interpreting ER diagrams.

• Follows conventional commit format and PR-based trunk workflow.

• Comfortable with AI-assisted development tools such as Claude Code and Cursor.

• Work authorization is required; visa sponsorship is not available.

• Knowledge of Kubernetes is a plus.

• Familiarity with AWS is advantageous.

• Conceptual understanding of OAuth2 / OIDC is beneficial.

• Experience with Terraform is an added advantage.

• Familiarity with LaunchDarkly is a plus.

• Experience in Document Intelligence / OCR is a plus.

🏝️ Benefits

• Fully remote work environment.

• Equal Opportunity Employer.

• Opportunities for professional growth.

• Commitment to diversity, equity, and inclusion programs.