Senior AI Engineer, Release Engineering

Quick Facts

• Role: Senior AI Engineer (Release Engineering)

Description

You will build and operate an internal, AI-powered agentic developer platform that automates development, release, and operational workflows. The work centers on designing reliable agents, prompts, MCP integrations, and the AI Development Life Cycle (AIDLC) with required security, evaluation, and auditability for privileged access. You will also ensure reliability and cost control via evaluation frameworks, tracing, and production health monitoring.

Role Description & Responsibilities

• Agent Platform: design, build, and maintain the agent API, MCP integrations, intent-routing logic, and an agent/skill registry.

• AIDLC & Agentic Workflows: design multi-step, tool-using agents; author and iterate prompts and skill/context definitions; plan for failure and recovery; build release and CI/CD agents for pipeline triage, release readiness, change documentation, and rollback assistance.

• Security & Governance: enforce least-privilege/zero-trust access with per-tool permissions; implement human-in-the-loop approvals for high-risk actions; protect against prompt injection and data leakage; provide audit logging and compliance controls.

• Evaluation, Reliability & Cost: build evaluation frameworks (evaluation sets, prompt regression tests, quality metrics), route/select models, manage caching/token budgets/cost attribution, and instrument tracing and structured logging.

• Adoption & Collaboration: contribute developer-facing interfaces (e.g., chat integrations), document reusable patterns, translate engineering needs into agents/skills, and maintain clean, tested, secure code through reviews.

Requirements

• Bachelor’s degree or equivalent combination of education and experience

• 5+ years professional experience in software engineering, DevOps, or release engineering (platform/internal tooling)

• Hands-on CI/CD and Git-based source control experience (GitHub preferred)

• Strong understanding of agentic patterns including planning, tool selection, multi-step tasks, agent-loop design, and failure modes

• Strong prompt engineering and context-window management skills (including scoped prompts/skill definitions)

• Knowledge of AI security risks such as prompt injection

• Daily use of AI coding tools (e.g., Claude Code, GitHub Copilot, Codex, Cursor, or similar)

• Experience building production or near-production agentic automation using LLM APIs with tool calling and structured output

• Practical experience with MCP or equivalent tool-calling frameworks (schema design, integration, scope management)

• Experience evaluating LLM outputs using evaluation sets, regression testing, and quality metrics

Benefits

• Opportunity to advance agentic AI in a platform engineering context by building an internal developer product (AIDLC) used across CI/CD, source control, ticketing, and deployment systems