Job
Full source details
✓ 100% verification score · Source: Clera (ashby) · Always confirm final requirements on the original source.
Complete source information imported
The available role or programme description, requirements, benefits and source facts were imported from the public official endpoint and formatted for reading.
EmploymentFull-time
Overview
ABOUT THE ROLE
Full job description
ABOUT THE ROLE This is a founding engineering role at an agentic integration platform operating in the flexible work and gig economy space. You will own the agent layer end-to-end, working directly alongside the CTO to build production systems that do real work with real consequences. It is an early, high-ownership position at the frontier of what agentic software can do at scale. WHAT YOU'LL DO
- Own the full agent layer: context engineering, self-learning systems, evals, the agent harness, and the meta-harness.
- Build a compounding knowledge base of undocumented systems so that each new integration benefits from everything learned before it.
- Design and ship self-healing workflows that detect, diagnose, and recover from production failures autonomously.
- Build and maintain the meta-harness that lets the team create, evaluate, and evolve new agents in days rather than weeks.
- Set the patterns and standards for how every agent at the company gets built, measured, and improved.
- Help grow the team and eventually lead the people who own agentic systems.
- Work as a peer to the founding team and experiment relentlessly. WHAT WE'RE LOOKING FOR
- 2 to 9 years of professional software engineering experience, with hands-on agentic software built within the last year.
- Strong CS fundamentals, ideally from a technical degree program at a well-regarded university.
- Comfortable with TypeScript and working with LLMs, evals, and agent tracing in production.
- Experience building context or self-learning systems that accumulate knowledge to improve agent performance over time.
- Demonstrated track record of shipping autonomous failure detection, diagnosis, or self-healing workflows to production.
- Harness-centric approach to agent building: eval-driven iteration, structured context engineering.
- Background at a startup (including YC or top-tier VC-backed companies) or direct founding experience is a strong signal; candidates who have spent their entire career at large tech companies or enterprises are unlikely to be a fit.
- Reusable agent harness or meta-harness experience is a plus. COMPENSATION & BENEFITS Salary range: $150,000 to $300,000 USD annually. Visa sponsorship (O-1) is available for qualified candidates with a concrete relocation plan. LOCATION On-site, five days a week in San Francisco, CA, United States. Candidates currently based elsewhere in the US are welcome with a concrete, dated relocation plan to San Francisco.
Tips for this job
Practical JobOpportunity guidance. These tips do not replace official rules or create new eligibility requirements.
- Tailor the CV and application to the responsibilities and required skills stated on the official employer page.
- Use concrete evidence of relevant work, projects and measurable results rather than generic claims.
- Confirm location, work authorization, remote restrictions and sponsorship terms before applying.
- Apply through the original employer or official recruitment destination shown on this page.
Verification notes
laptop-ats-crawler v3
Original authoritative source
JobOpportunity is the discovery and verification layer. Confirm eligibility, dates, salary/funding and application instructions on the original source before submitting anything.
Apply through JobOpportunity →