AI Evaluation Engineer: Scalable Evals & Benchmarks

Glean; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Glean is seeking an experienced инженер to own eval sets, benchmarks, and the platform that powers evaluation of our AI products. You will build agentic verifiers, CAD-like pipelines, dashboards, and simulations to test multi-step agent tasks at scale.

You will work with R&D, product, and GTM to turn eval insights into better products and customer outcomes, ensuring measurement quality across the stack and CI/CD integrations.

Qualifications

• Experience building eval or experiment infrastructure that runs reliably at scale, including CI/CD integrations and observability tooling like OpenTelemetry.
• 5+ years of software engineering experience with strong Go and/or Python and backend fundamentals: APIs, data modeling, testing, and distributed pipelines.
• Experience building datasets and benchmarks for LLM use-cases, RAG, or agents, including evalset curation and synthetic data generation.
• Familiarity with eval methodologies and their tradeoffs: deterministic metrics, LLM-as-a-judge, pointwise vs pairwise grading, human labeling, and judge calibration.
• Strong analytical skills: you dig into traces and failure cases, write SQL, and use data and metrics to explain why quality moved.
• Nice to have: experience with simulation environments and/or model post-training techniques.

Responsibilities

• Own the design and implementation of eval sets and benchmarks from expert-curated, production, synthetic data, and edge cases.
• Scale the eval platform and agent observability: pipelines, trace capture/replay, dashboards for reproducible runs.
• Build agentic LLM verifiers for correctness, groundedness, citations, and task success; calibrate them against human labels.
• Run evals across CI, pre-release, and sampled production traffic; report results with confidence intervals.
• Create enterprise simulation environments with realistic company data to test multi-step agent tasks.
• Diagnose failures by slice and trace; translate eval results into concrete fixes balancing quality, latency, and cost.

Job description

Glean is seeking an experienced инженер to own eval sets, benchmarks, and the platform that powers evaluation of our AI products. You will build agentic verifiers, CAD-like pipelines, dashboards, and simulations to test multi-step agent tasks at scale.

You will work with R&D, product, and GTM to turn eval insights into better products and customer outcomes, ensuring measurement quality across the stack and CI/CD integrations.