Founding RL Environments Engineer - Benchmarks & Evals

Rnb Consultancy; San Francisco (CA); On-site; USD 150,000 - 200,000; Full time

Benefits offered by this job

Base salary $150k–$200k

Equity 0.25–0.5%

Profit sharing up to 4% of project

Founding role with frontier labs

Job summary

Rnb Consultancy in San Francisco invites an experienced AI software engineer to build RL environments and benchmarks for frontier models. As the first engineer in SF, you will design tasks, eval harnesses, and post-training experiments, and by month six lead a team.

The role demands full-time on-site work in SF with a 9-9-6 schedule. Base salary ranges from $150k to $200k plus equity (0.25–0.5%), and a potential 4% profit share that could push total pay toward $500k annually.

Qualifications

• Built RL environments, tasks, benchmarks or evaluation harnesses with your own hands.
• Hands-on post-training experience (SFT, DPO, GRPO, RLHF or similar) with tangible results.
• Able to work full time from the San Francisco office now, on a 9-9-6 schedule.
• Roughly 1–5 years of experience.

Responsibilities

• Design RL tasks and environments that frontier models train on.
• Develop eval harnesses and benchmarks to show model improvements.
• Conduct post-training experiments and translate findings into better environments.
• Hire and lead a team in San Francisco as the company grows.

Skills

RL environments

Post-training experience

Team leadership

Founding team mindset

Job description

Rnb Consultancy in San Francisco invites an experienced AI software engineer to build RL environments and benchmarks for frontier models. As the first engineer in SF, you will design tasks, eval harnesses, and post-training experiments, and by month six lead a team.

The role demands full-time on-site work in SF with a 9-9-6 schedule. Base salary ranges from $150k to $200k plus equity (0.25–0.5%), and a potential 4% profit share that could push total pay toward $500k annually.