Harness Engineer, AI Workflows & Release Automation

AI Fabrik

San Francisco (CA)

On-site

USD 180,000 - 240,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

AI Fabrik is hiring to own our engineering harness—tooling and AI workflows spanning the full delivery pipeline. You will boost velocity by reducing handoffs and bottlenecks using AI agents and automation, from requirements to release, with emphasis on speed, reliability, and safe operation.

The role emphasizes practical impact: identifying where teams waste time and delivering infrastructure that accelerates shipping and reduces manual effort, while maintaining strong governance and measurable

Qualifications

3+ years of professional software engineering experience, with a strong background in developer tooling, platform engineering, or DevOps.
Proficiency in at least one mainstream programming language such as Python or Go.
Hands‑on experience integrating with major LLM API (OpenAI, Anthropic, or Google).
Solid understanding of production reliability patterns: retry logic, circuit breakers, rate limiting, timeout handling, and graceful degradation.
Experience with CI/CD pipeline design and the full software delivery lifecycle.
Experience with monitoring, logging, and observability of production systems.
Strong written communication skills — document architectural decisions, constraints, and harness behaviour clearly.

Responsibilities

Identify bottlenecks across the full software delivery lifecycle and build AI‑assisted harnesses with measurable impact (cycle time, lead time, defect rate, deployment frequency).
Build harnesses for AI‑assisted requirements elaboration, automated design review, specification validation, and artefact generation.
Design and maintain agent environments supporting day‑to‑day development: code generation, automated refactoring, test authoring, and documentation.
Build agent‑assisted release workflows, automated pre‑deployment checklists, rollback triggers, and progressive rollout controls to reduce manual effort.
Define good output at each pipeline stage and enforce it via evaluation datasets, grading rubrics, and CI/CD‑integrated quality gates.
Instrument harness components with structured logging and quality metrics to identify underperformance and opportunities for improvement.
Implement permission boundaries and human‑in‑the‑loop checkpoints to keep agents safe without sacrificing speed.
Apply token budgeting, caching, model tiering, and budget controls to manage runaway LLM costs.