Job description
We are seeking a hands-on Technical Lead to spearhead the architecture, development, and delivery of our enterprise Agent Deployment Framework and Active Data Products. In this role, you will lead a team of senior Python and cloud engineers focused on extending our existing Python-based DPS framework into a resilient, scalable, self-service platform. This platform will enable internal developer teams to build, test, and deploy AI agents, Model Context Protocol (MCP) integrations, and Slack applications effortlessly.
The ideal candidate is a seasoned software architect and player-coach who thrives on distributed systems engineering, clean API design, and enterprise-grade automation. You will ensure that hundreds of independently owned agent packages can safely deploy to AWS AgentCore and Slack runtimes without requiring changes to shared platform code.
Technical Direction
Define the technical vision and architectural roadmap for the Agent Deployment Framework and Active Data Products.
Team Management & Mentorship
Lead, unblock, and conduct rigorous code reviews for a high-performing team of Python, backend, and integration engineering contractors.
Developer Experience (DX)
Champion a seamless DX where developers author YAML configs, agent instructions, and tests, while the core platform abstracts away deployment, auth, and infrastructure complexities.
CLI Tooling & Automation
- Oversee and contribute to the development of robust CLI tools for package initialization, schema validation, local readiness checks, and live statlogging retrieval.
Enterprise CI/CD
- Architect reliable GitHub Actions-based YAML deployment pipelines that flawlessly handle multi-environment updates, failure detection, and automated rollbacks.
Distributed Systems Security
- Enforce secure credential management, ensuring agent owners manage their own AWS Secrets Manager secrets via approved logical platform bindings.
Integration Frameworks
- Design reusable capabilities for Model Context Protocol (MCP), Slack APIs, asynchronous streaming, and complex per-user OAuth/OIDC flows.
Platform Multi-Tenancy
- Ensure the core runtime securely isolates and supports hundreds of independent agent packages without monolithic overhead or global codebase alterations.
Observability
- Implement comprehensive tracking, metrics, and logs across AWS ECS/Fargate, Lambda, and CloudWatch to ensure total operational visibility.
Deliver reliable GitHub Actions based deployments
- with testing, approvals, promotion, rollback, and SOX evidence.
Extend ingestion
- dbt, Snowflake Dynamic Tables, data-quality, freshness, and self-healing capabilities.
Implement Governance as Code
- including RBAC, ownership, SFSS-019 classification, PII, lineage, and catalog metadata.
Support Tableau semantic models
- through OSI/OSSIE and governed MCP/Slack activation.