Python Developer – Agentic AI Infrastructure (AI/LLM Engineer) - Local/Hybrid
About the position This role will design, build, and operate production-grade agentic AI solutions and supporting infrastructure using Python. You will develop AI agents and workflows that securely leverage institutional data, systems, and tooling to automate routine technical and operational work, accelerate delivery of AI-enabled capabilities, and enable broader adoption through reusable components and patterns. This is a hands-on engineering role focused on taking concepts from prototype to production—iterating quickly while meeting enterprise expectations for security, reliability, maintainability, and documentation.
Responsibilities
- Design and implement agentic AI workflows and services in Python , including tool- using agents, orchestrated multi-step processes, and integration patterns.
- Build and maintain reusable frameworks/components for agent development (e.g., agent runners, tool registries, prompt/config management, evaluation harnesses).
- Integrate agents with enterprise data sources and systems in a secure, auditable manner (APIs, services, databases, and internal platforms as applicable).
- Develop and harden AI-enabled applications and supporting APIs for internal use, including deployments to OpenShift.
- Implement best practices for production readiness: testing, logging/metrics, error handling, performance considerations, and operational run books.
- Contribute to platform standards and reference implementations for agentic development (including patterns aligned with Model Context Protocol where applicable).
- Collaborate with stakeholders to translate use cases into technical requirements, iterate on solutions, and deliver measurable outcomes.
- Ensure appropriate documentation for all development and modifications, including architecture notes and operational guidance.
- Ensure integrity, confidentiality, and security of institutional data used by AI solutions (data handling, access controls, and policy-aligned implementations).
Requirements
- Professional experience developing production Python applications/services.
- Familiarity with Model Context Protocol (MCP) concepts and patterns.
- Experience implementing AI/LLM solutions (at least one of: agents, RAG pipelines, tool/function calling, workflow orchestration, LLM evaluation).
- Strong software engineering fundamentals: version control, code review, testing, documentation, and secure coding practices.
- Ability to work collaboratively across technical and non-technical stakeholders to deliver iterative outcomes.
Nice-to-haves
- Familiarity with AI-assisted development tools (e.g., Claude Code, OpenAI Codex, GitHub Copilot) for tasks such as refactoring, test generation, debugging, and documentation.
- Experience with agentic development frameworks and/or building internal frameworks for reuse.
- Experience with Azure AI tooling (including Azure AI Foundry ) and deploying LLM-backed solutions in enterprise environments.
- Experience integrating or extending Open WebUI (or similar internal chat/LLM front-ends ).
- Open source experience (contributing to projects, maintaining internal open-source-style libraries, or publishing reusable tools).
- Experience with OpenShift and Kubernetes -native application patterns (health checks, resource limits, secrets/config management).
Apply tot his job Apply To this Job