Founding Engineer: AI Evaluation Environments & Data

CLERA; San Francisco (CA); On-site; USD 200,000 - 300,000; Full time

Benefits offered by this job

Founding equity

Visa sponsorship

Job summary

Clera Labs, Inc. in San Francisco is seeking a founding engineer to build evaluation environments and benchmarks that measure whether AI agents can perform real-world company work and meet or exceed human performance.

You will design synthetic company environments with realistic emails, records, and files for agents to use over extended periods. You will build graders and evaluation systems capable of assessing advanced agents, including cases where human reviewers may lack the relevant

Qualifications

• Hands-on research experience in synthetic data pipelines, benchmarks, evaluations, or model post-training.
• Experience building environments or benchmarks used to train or evaluate agents in an AI lab.
• 1–2 years at a fast-growing or AI-focused startup with mid-level or senior engineering or research experience.
• Degree from a highly selective university or equivalent credential (founding a company or founder programs count).
• High-level competition experience in math, programming, debate, or games is a plus.

Responsibilities

• Design synthetic company environments with realistic emails, records, and files for agents to use over extended periods.
• Build graders and evaluation systems capable of assessing advanced agents and cases where human reviewers lack expertise.
• Develop benchmarks that correlate with real-world production performance.
• Find and address evaluation failure modes, including reward hacking and benchmark gaming.
• Simulate software tools such as inboxes and CRMs to support agent interactions at scale.

Skills

Synthetic data pipelines

Benchmarks

Grading systems

Agent evaluation

Education

Selective university degree

Job description

Clera Labs, Inc. in San Francisco is seeking a founding engineer to build evaluation environments and benchmarks that measure whether AI agents can perform real-world company work and meet or exceed human performance.

You will design synthetic company environments with realistic emails, records, and files for agents to use over extended periods. You will build graders and evaluation systems capable of assessing advanced agents, including cases where human reviewers may lack the relevant