Santa Clara, CA

Salary
$166,500–$291,400from the description
Posted
Jul 19, 2026
Location
Santa Clara, CA
Last confirmed open
Jul 21, 2026

What this job asks for AI summary

A people-management role leading an 8-engineer team responsible for the evaluation framework, model benchmarking, and telemetry for an AI coding assistant built on a metadata-driven platform. Day-to-day work spans designing prompt sets and scoring methodologies, assessing candidate foundation models against a production default, tracking inference cost and correctness as release signals, and driving cross-team accountability to turn evaluation findings into committed fixes. Suits someone with hands-on LLM evaluation experience and proven engineering management background.

Senior level · 6+ years · San Jose-Sunnyvale-Santa Clara, CA · Full-time

Must have (4)
LLM evaluation systemsLLMsJava, C++, Ruby, Shell Scripting or JavaScriptfoundation model evaluation
Nice to have (2)
ServiceNowtelemetry instrumentation

“or” means any one of them counts — you don't need all of them.

Posted 2 times — it's one opening, so apply once.

We read this from the posting text with AI. Skim the description below before ruling yourself out.

How this req sits in the market our data

Roughly 590 people in the San Jose-Sunnyvale-Santa Clara, CA area plausibly meet what this posting asks for (computer and information systems managers). range 220–770

Applicant volume Moderate — A normal amount of company. The rare requirements below are what will separate a shortlisted application from the rest.

What won't set you apart
Java62%

Most people in this occupation already list these. Still required — just not what gets you shortlisted.

What the occupation pays Median $298,074 (middle half $224,695–$326,567). This posting is about at that midpoint.

Estimated from BLS employment for this occupation and area, per-skill prevalence across our listing corpus, and published wage benchmarks — as of Jul 28, 2026. It is a model, not a headcount.

Why we read it this way (9)

This role is primarily a people-management position (managing an 8-engineer team, staffing, mentoring, performance management), which maps to 11-3021. However, the JD also demands deep hands-on technical expertise in LLM evaluation systems and coding agent architecture, making 15-1299 (Computer Occupations, All Other) a plausible runner-up for the IC-leaning technical work described.

The 6+ years experience requirement is stated as '6+ years of experience with technologies relevant to ServiceNow' — this is a technology-experience gate, not a pure role-level gate, but it is the closest stated overall experience figure and is used as the overall years minimum.

Java is listed as the primary named language in a required 'or' group ('Java, C++, Ruby, Shell, or JavaScript'); the others are captured as alternatives since fluency in any one satisfies the requirement.

'Coding agent architecture' and 'foundation model evaluation' are retained as skills because the JD uses firm gating language ('working understanding of…' and 'experience critically evaluating…') in the qualifications block, even though they are not conventional tool names — they represent concrete, named technical competencies the JD explicitly gates on.

ServiceNow platform knowledge is implied throughout but never stated as a hard gate in the qualifications section; it is marked preferred.

Telemetry instrumentation and benchmark design appear as responsibilities/focus areas rather than explicit qualifications gates, so they are marked preferred.

Location is inferred as ServiceNow's headquarters (Santa Clara, CA) based on the compensation disclosure referencing a specific geographic location; the posting does not explicitly name a city but the pay range and company HQ point to the San Jose-Sunnyvale-Santa Clara CBSA. The work persona policy suggests this may not be fully remote.

People management experience is explicitly required ('People management experience is required'); managing 8+ engineers or managing managers is listed as a plus.

Ignored 2 non-technology phrase(s) as skills (responsibilities/concepts, not named tools): coding agent architecture, benchmark design.

Read the full posting

The employer publishes the full description on their own site — read it there ↗. Or sign in to read it here — it's free, and it also lets you track this application.

Apply

Apply on employer site ↗