Software Engineer, RL Environments

David Joseph & Company; San Francisco (CA); On-site; USD 180,000 - 220,000; Full time

Job summary

David Joseph & Company in San Francisco, CA is seeking a SWE (Environments) to design datasets and evaluation rubrics that influence frontier model training. You will move quickly from hypotheses to live experiments, with outputs feeding model training at scale.

The role demands 1–4 years of software engineering experience, ownership of end‑to‑end data pipelines, and the ability to design lightweight experiments across finance, code, and enterprise workflows.

Qualifications

• 1–4 years of software engineering experience with strong technical depth.
• Design targeted data slices that surface model failure modes across high‑stakes domains.
• Build and iterate on evaluation rubrics and reward signals powering RLHF and RLVR pipelines.
• Develop quantitative frameworks to measure dataset quality, diversity, and downstream impact on model alignment and capability.
• Own end‑to‑end real world and synthetic data pipelines from scoping with research teams to production‑ready evaluation specs.

Responsibilities

• Design data slices and explore data shapes to reveal model failure modes in domains like finance, code, and enterprise workflows.
• Build and refine evaluation rubrics and reward signals for RLHF/RLVR training pipelines.
• Model annotator behavior and run experiments to improve model capabilities.
• Develop quantitative frameworks to measure dataset quality and downstream impact on alignment and capability.
• Create and manage both real‑world and synthetic data pipelines.

Skills

Software engineering

Data pipelines

Experiment design

RLHF pipelines

Model evaluation

Job description

San Francisco, CA · On-site · Full-time
Compensation: $180,000–$220,000 + competitive equity

About the Company

An early-stage (post–Series A) company building the training data and evaluation infrastructure that frontier AI labs use to improve their models — designing high-signal datasets and running rigorous evaluations that go beyond static benchmarks. A small team where individual contributors have direct impact on how the next generation of models learns. The company has raised $30M (~$300M valuation), with a founding team drawn from Jane Street, Citadel, Google, Goldman, and Stanford AI Lab.

Founded 2025 · 11–50 people · Industry: Consumer Tech

The Role

As a SWE (Environments), you'll design the datasets and evaluation rubrics that directly influence how frontier models learn — going from hypothesis to live experiment quickly, with output feeding directly into model training runs at scale.

What you'll be doing

• Design data slices and explore data shapes that expose meaningful model failure modes across domains like finance, code, and enterprise workflows
• Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines
• Model annotator behavior and run experiments to improve different model capabilities
• Develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on model alignment and capability
• Create and manage both real‑world and synthetic data pipelines
• Partner with lab research teams to translate their training objectives into concrete data and evaluation specifications

Tech stack: Not specified

Requirements

• 1–4 years of software engineering experience with strong technical depth
• Design targeted data slices that surface model failure modes across high‑stakes domains (finance, code generation, enterprise workflows)
• Build and iterate on evaluation rubrics and reward signals powering RLHF and RLVR training pipelines
• Develop quantitative frameworks to measure dataset quality, diversity, and downstream impact on model alignment and capability
• Own end‑to‑end real world and synthetic data pipelines, from scoping with research teams to production‑ready evaluation specs
• Run annotator modeling experiments to improve model capabilities across task types

Green Flags

• Experience at RL environment companies
• Background in AI safety or benchmarking organizations like METR or Artificial Analysis
• Genuine obsession with how data structure, selection, and quality drive model behavior
• Ability to design lightweight experiments and move fastFormer founders or early engineers at early stage startups
• Demonstrated ability to work hard, learn fast, and care deeply about details

Red Flags

• Pure research profile with limited engineering output, this is a SWE role, shipping matters
• Looking for standard product engineering work — the real scope is data pipelines, reward modeling, and eval infra

Why Join

• Outsized total cash: base plus substantial profit share, plus competitive equity
• Direct impact on frontier AI model development, working with the world's leading AI labs
• High ownership on a small, early team — scope, build, and ship end to end

Details

• Location: San Francisco, CA
• Work policy: On-site
• Compensation: $180,000–$220,000 + equity
• Visa sponsorship: O-1, OPT
• Employment type: Full-time