JobHabor
Menu

Software Engineer, RL Environments

True Talent Solutions Partners · San Francisco · Onsite

Strong hiring record · median 1 days open

100100

Hiring signal

Actively hiring

Posted today · Reposted 3× · Checked today · How we score

First seen
19 November 2026
Reposted
3× since September 2026
Last checked
Today · still on the employer's board
All reasons
  • This role has been posted 3 times

In its favour

  • Posted today
  • Still listed on the employer's own board
  • Publishes a salary range

Did you apply?

Software Engineer, RL Environments at True Talent Solutions Partners. We’ll keep it in your applied jobs, so you can see it later and be warned before applying to the same employer twice.

About the Role

Build datasets, evaluation rubrics, and infrastructure that help improve advanced AI models. You will work with research teams to run experiments, identify model failure modes, and turn training objectives into practical data and evaluation systems.

What You'll Do

  • Design data slices that reveal meaningful model failure modes across finance, code, and enterprise workflows.
  • Build and refine evaluation rubrics and reward signals for RLHF and RLVR pipelines.
  • Model annotator behavior and run experiments to improve model capabilities.
  • Develop quantitative measures of dataset quality, diversity, and impact on model alignment and capabilities.
  • Create and manage real-world and synthetic data pipelines.
  • Partner with AI research teams to translate training goals into concrete data and evaluation specifications.

What We're Looking For

  • One to four years of software engineering experience building reliable data pipelines, experimentation infrastructure, or evaluation systems.
  • Strong Python skills and experience shipping software and infrastructure.
  • Hands-on experience with LLM evaluations, model post-training, reward modeling, RLHF, RLVR, or related ML infrastructure.
  • Experience creating or evaluating datasets, including assessing quality, diversity, coverage, and downstream model performance.
  • Strong experimental judgment: able to form hypotheses, define metrics, design controlled experiments, and interpret noisy results.
  • Experience designing data collection strategies and evaluation rubrics for machine learning models.

Compensation & Benefits

Base salary

$260,000 to $290,000 annually. Visa sponsorship is available.

Location

On-site in San Francisco, California.

More jobs at True Talent Solutions Partners

All 90

Similar roles