Destava

Member of Technical Staff - ML Platform Engineer

Preference Model is hiring for Member of Technical Staff - ML Platform Engineer in San Francisco. Staff level. First seen November 11, 2026, posted 3 times; open as of November 18, 2026. Jobs taken straight from company career pages — no aggregator in between.

Save to applyFree forever. No commitment, no card required.

Company
Preference Model
Where
San Francisco
Type
Full-time
Level
Staff
First seen
November 11, 2026
Postings
3
Listed via
Ashby
Open for
7 days, as of November 18, 2026

About this job

This is a senior ML platform engineering position at a San Francisco AI research startup. You will be responsible for the systems that package, validate, and deliver reinforcement learning environments to partner labs, collaborating with environment builders and researchers. As part of a small Platform team, you will build internal tools and infrastructure.

Responsibilities

  • Manage integrations delivering environments to partner labs, including image creation, format alignment, and automated checks, with manual steps as needed.
  • Develop and maintain Karotte, our open-source environment framework, covering API design, releases, and migrations ensuring backward compatibility.
  • Operate and scale the infrastructure for building, running, and grading environments, including containerized deployments, CPU/GPU/TPU grading, VM sandboxing, and resource controls.
  • Create internal tools for environment builders, such as CLI, documentation, data catalogs, access management, and run monitoring, to reduce infrastructure overhead.
  • Collaborate with environment builders and post-training researchers to convert recurring issues into platform features and iterate rapidly on feedback.

Requirements

  • At least five years of experience owning ML Platform Engineering, with a preference for AI-focused roles.
  • Solid software engineering skills and a history of building and maintaining production infrastructure or developer platforms relied upon by others.
  • Practical experience with containerization and orchestration tools like Docker or Kubernetes, plus a major cloud provider such as GCP or AWS.
  • A solid grasp of safely executing untrusted code, covering isolation, resource constraints, and handling processes that exhaust disk or hang.
  • You have fully owned a tedious process like a migration, release, or delivery pipeline, and automated it as much as possible.
  • Extensive daily use of coding agents such as Claude Code, Cursor, or Codex, with a sense for where they take shortcuts.
  • Strong Python skills, including creating libraries and APIs that others build upon.

Nice to have

  • Prior work on RL environments, evaluation harnesses, or agent benchmarks such as Terminal-Bench or SWE-bench.
  • Knowledge of RL post-training and inference systems including verl, Ray, SkyPilot, vLLM, or SGLang.

Benefits

  • Cash and equity compensation that is highly competitive, exceeding the 90th percentile.
  • A fast-paced startup setting where you will have significant ownership and independence.
  • Collaborate with senior and staff engineers from leading labs and infrastructure firms, as well as top ML talent.
  • Comprehensive medical, vision, and dental coverage.
  • Employer matching contributions to your 401K plan.
  • Daily on-site lunch is provided.
  • Snacks are ordered on a weekly basis.
  • Visa sponsorship and relocation assistance are available.

Read more and apply on Preference Model's site

Questions about this job

When was this Member of Technical Staff - ML Platform Engineer job at Preference Model posted?

Destava first saw it on November 11, 2026, on Preference Model's own careers page (Ashby). Preference Model has listed this job at this place 3 times in the last 90 days, counting the ones taken down.

Is Preference Model still accepting applications for it?

It was open on Preference Model's own site when Destava last read it, on November 18, 2026, 7 days after we first saw it. When the company takes it down, this page says the job has closed.

How do I apply for Member of Technical Staff - ML Platform Engineer at Preference Model?

On Preference Model's own site, at jobs.ashbyhq.com: open the posting. Destava does not take the application. Save the job to your Destava board to track it, see how well you fit and tailor your résumé to it.

Is this Preference Model job posting legit?

Destava read it on Preference Model's own careers page at jobs.ashbyhq.com, run on Ashby, not on a job board. First seen November 11, 2026, posted 3 times. Apply on the company's own site, and never pay to apply for a job.

What other jobs is Preference Model hiring for?

Preference Model has 6 open postings on its own site: see all jobs at Preference Model.

Applying to this one?

See how well you fit, before you apply

Save it to your board. Add your résumé once, and Destava shows where you are strong, what is missing and how to pitch yourself, then tailors your résumé to this posting.

  1. Found it
  2. Save it
  3. See your fit

Free forever. No commitment, no card required.

Or apply on Preference Model's own site

With Destava: Save to apply · Tailor my résumé · Write a cover letter

This page includes information from the O*NET 31.0 Database by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA). Used under the CC BY 4.0 license. O*NET® is a trademark of USDOL/ETA.