Omri Levi
Built three production AI agents. Job title says Support Engineer.
Verified skills
Each of these was earned on a timed challenge and scored against a rubric that was published before the challenge started. The work is attached — you can read it.
Sets the architecture and safety boundaries other teams build against, and designs for observability and recovery from day one.
Verified at Level 4 on Ship an AI Agent — tool withholding, approval boundaries, and failure design.
Makes justified trade-offs between model tiers, caching, and retrieval, and designs explicit fallback behaviour for model failure.
Separated deterministic logic from model judgment explicitly and correctly.
Designs evals that target real failure modes, chooses metrics that resist gaming, and knows the limits of what the eval measures.
Boundary-weighted eval set with an asymmetric, justified launch bar.
Decomposes unreliable tasks into verifiable steps, chooses between prompting, tool use, and retrieval on the merits, and builds a small evaluation set before changing anything.
Encoded policy for consistent application; defined behaviour for ambiguous input.
Claimed, not yet verified
Self-reported — the same standing as anything on a CV. Shown here for completeness and clearly separated, because a verified section only means something if the unverified one is honest.
Work samples
Unedited submissions, with the rubric score attached.
Closest role fits
Scored against published role specs. Every number is itemised on the role page.
This profile is evidence, not a CV. Anything marked verified can be checked by reading the work.