Destava

Member of Technical Staff - ML Infrastructure Engineer, RL Post-training

Preference Model is hiring for Member of Technical Staff - ML Infrastructure Engineer, RL Post-training in San Francisco. Staff level. First seen November 12, 2026, posted 3 times; open as of November 19, 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 12, 2026
Postings
3
Listed via
Ashby
Open for
6 days, as of November 19, 2026

About this job

This is a senior infrastructure engineering role at a San Francisco AI research startup. You will build the compute, data, and tooling systems that power reinforcement learning for large language models. The job is full-time and onsite, with daily lunch provided.

Responsibilities

  • Design, build, and scale the compute, scheduling, and data systems for post-training research
  • Develop and maintain core ML framework tools and internal utilities for researchers
  • Build evaluation, benchmarking, monitoring, logging, debugging, and automated testing/deployment systems
  • Work directly with Research Engineers to turn research needs into infrastructure plans and ship quickly

Requirements

  • Strong software engineering fundamentals and hands-on experience building production-grade LLM inference and training infrastructure, ideally from scratch
  • Experience building LLM training/inference internals like transformers, distributed training, and inference libraries such as vLLM, SGLang, Megatron
  • Experience with RL training frameworks like Slime, veRL, Ray Train, SkyRL, Miles
  • Significant experience with distributed systems principles and hands-on cloud (AWS, GCP) and Kubernetes experience for high-throughput, low-latency workloads
  • Experience with data engineering tools and building robust, scalable data pipelines
  • Proficiency in core ML frameworks such as PyTorch or JAX
  • Ability to balance production rigor with fast-moving research pace and communicate infrastructure tradeoffs clearly to non-infra researchers

Benefits

  • Competitive cash and equity compensation (>90th percentile)
  • Ownership and autonomy in a fast-moving startup
  • Opportunity to work alongside senior and staff engineers from frontier labs and infrastructure companies, plus top ML engineers
  • Health, vision, dental benefits
  • 401K match
  • Lunch provided everyday onsite
  • Weekly snack orders
  • Visa sponsorship & relocation support available

Read more and apply on Preference Model's site

Questions about this job

When was this Member of Technical Staff - ML Infrastructure Engineer, RL Post-training job at Preference Model posted?

Destava first saw it on November 12, 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 19, 2026, 6 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 Infrastructure Engineer, RL Post-training 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 12, 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.