Founding Engineer, Environments and Data
At a glance
Mid-level Software Engineering role at Clera. San Francisco · full-time · $200,000–$300,000 base.
techroles summary, based on the employer's posting.
What you'll do
- Create workplace simulations containing realistic messages, records and files for agents to handle over lengthy assignments
- Build reliable methods for scoring advanced agents and tests that reflect how they perform in production
- Spot ways agents can manipulate evaluations, then close reward-hacking and benchmark-gaming loopholes
- Reproduce inbox and CRM software so agents can interact with realistic tools at scale
What you bring
- Mid-level or senior engineering or research experience, with at least one to two years at a fast-growing or AI-focused startup
- Hands-on AI work involving synthetic data pipelines, benchmarks, evaluations or post-training
- You have built agent-training or evaluation settings and implemented systems that grade agent performance
- Your background includes research-focused work, such as simulating software for agents or finding flaws in existing benchmarks
Who this fits
This suits a research-oriented engineer focused on measuring agent capability, not someone seeking infrastructure work alone. You’ll work on-site five days each week in San Francisco. Visa sponsorship is available.
From the employer
About the Role
Build evaluation environments and benchmarks that measure whether AI agents can perform real-world company work and match or exceed human performance. This founding engineering role focuses on agent capability assessment and production readiness, with work that shapes how agent competence is measured.
What You'll Do
Design synthetic company environments with realistic email, records, and files for agents to use over extended tasks.
Build graders and evaluation systems that can reliably assess advanced AI agents.
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 with enough fidelity to support agent interactions at scale.
What We're Looking For
Mid-level or senior engineering or research experience, including at least 1 to 2 years at a fast-growing or AI-focused startup.
Hands-on AI research or engineering experience with synthetic data pipelines, benchmarks, evaluations, or post-training. This is a research-oriented role, not solely infrastructure engineering.
Experience building environments or benchmarks used to train or evaluate agents, and designing and implementing agent graders or evaluation systems.
Experience simulating complex software systems for agent tool use, identifying flaws in established benchmarks, and detecting and fixing reward hacking.
Background in AI evaluation, benchmark design, simulation, agent systems, or related areas. Startup founding or accelerator experience and high-level competition experience in mathematics, programming, debate, or games are valued.
Collaborative, adaptable, and effective in a fast-moving environment.
Compensation & Benefits
Base salary is $200,000 to $300,000 annually, with up to $350,000 for exceptional candidates. Additional commission-style bonus compensation of up to $200,000 or more is tied to the value of delivered environments. Meaningful founding equity is included. Visa sponsorship is available.
Location
On-site five days a week in San Francisco, California, United States.