Sign up to access all features of our service.
  • Job search
  • Favorites
  • Create a CV
    New
  • Salaries
  • Subscriptions

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

Full-time

preference-model

About Us

Preference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.

Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.

We're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.

Over the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.

About the Role

Frontier research moves only as fast as its infrastructure permits. Building solid infrastructure is foundational to our mission of pushing self-directed learning as far as it can go.

We are looking for Senior ML Infrastructure Engineers to build the infrastructure and systems that power the frontier of post-training on large language models . This role involves building scalable infrastructure to enable high-throughput systems and shape how our research is run, bringing us closer to models that can train themselves on what they aren't yet good at.

 

What You Will Do
  • Design, build, and scale the compute, scheduling, and data infrastructure that powers post-training research on our in-house RL environments

  • Develop and maintain core ML framework primitives and internal tooling that researchers rely on daily, accelerating reproducible experimentation and reducing time from idea to result

  • Build evaluation and benchmarking infrastructure, monitoring, logging, and debugging tooling, and automated testing and deployment systems, so failures are caught early and infrastructure stays reliable as it scales

  • Partner directly with Research Engineers to translate research needs into infrastructure requirements, and ship fast in response to their feedback

What We are Looking For
  • Strong software engineering fundamentals and hands-on experience building production-grade LLM inference and training infrastructure (ideally from the ground up)

  • Experience building LLM training/inference internals such as transformers, distributed training, and working on inference libraries like vLLM, SGLang, Megatron

  • Experience working on RL training frameworks like Slime, veRL, Ray Train, SkyRL, Miles

  • Significant experience and understanding of distributed systems principles, and have hands-on experience with cloud platforms (AWS, GCP) and container orchestration (Kubernetes), building systems for high-throughput, low-latency workloads

  • Have experience with data engineering tools and building robust, scalable data pipelines

  • Proficiency in core ML frameworks such as PyTorch or JAX

  • Can balance production rigor with the pace of fast-moving research, and communicate infrastructure tradeoffs clearly to researchers who aren't infra specialists

What We Offer:
  • Competitive cash and equity compensation (>90th percentile)

  • Ownership and autonomy in a fast moving startup environment

  • 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

We value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply.

Vacancy posted 2 days ago
Similar jobs that could be interesting for youBased on the Member of Technical Staff - ML Infrastructure Engineer, RL Post-training in San Francisco, CA vacancy
  •  ...company. We build RL environments for training capable, better-...  ...building data infrastructure, and datasets behind...  ...an MTS on our ML Platform team ,...  ...ML platform engineering role where you...  ...environment builders and post-training...  ...alongside senior and staff engineers from... 
    Training
    Full time
    Immediate start
    Visa sponsorship
    Relocation package
    Shift work

    preference-model

    San Francisco, CA
    10 days ago
  • $200k - $350k

     ...is a research-first role, not an engineering role: you'll own Pantheon's offline RL research end to end, working alongside...  ..., MuJoCo, Brax, JAX, distributed training. Open to visa sponsorship (H1B...  ...Francisco. Interview: screening, technical chat with the RL research lead, 6... 
    Training
    Full time
    H1b
    Work at office
    Visa sponsorship

    Pantheon

    San Francisco, CA
    11 days ago
  •  ...We develop the infrastructure that enables intelligent...  ...from robotics training and simulation...  ...for exceptional engineers to help build...  ...We are hiring a Member of Technical Staff to lead reinforcement...  ...agentic model post-training. You...  ...larger-scale RL across both digital... 
    Training
    Full time

    embedding-vc

    San Francisco, CA
    7 days ago
  • $200k - $400k

     ...Company Pilots don't train with real...  ...funding, with a $2B post-money valuation in...  ...About the Team The Infrastructure team is the...  ...empower our entire engineering org to ship safely...  ...Ability to write clear technical specs for both...  ...Nice to Haves AI/ML Infrastructure: Experience... 
    Training
    Full time
    Flexible hours

    simile

    San Francisco, CA
    7 days ago
  • $150k - $220k

    # Founding Member of Technical Staff (MTS)Bay Area, CAFull...  ...security, and infrastructure best practices...  ...deep AI/ML research leadership...  ...MLE + backend engineering with a strong...  ...services for training, evals,...  ...Experience with RL, reward modeling...  ...Lightning* •LLM post-training exposure... 
    Training

    Vizops

    San Francisco, CA
    1 day ago
  •  ...About the Role Member of Technical Staff is a generalist position...  ...out durable agentic infrastructure for long-horizon tasks. Post-training. Create post-training...  ...recipes using pipeline RL and make...  ...utilization Context Engineering. Automate ingestion of... 
    Training

    Ripline

    San Francisco, CA
    1 day ago
  •  ...Perplexity is seeking experienced ML engineers to design, build, and optimize the recommendation...  ...with usage. Help shape the technical direction of ranking, recommendations...  ...with large-scale ranking and training infrastructure (multi-stage retrieval and ranking, feature... 
    Training
    Full time

    Perplexity

    San Francisco, CA
    11 days ago
  • $240k - $350k

     ...run by scientists and engineers from leading...  ...About the Role As a Member of Technical Staff, Machine Learning Engineer...  ...environments in which to train and deploy AI agents...  ...building internal infrastructure to improve the efficiency...  ...of work in applied ML research and... 
    Training
    Full time
    Work at office
    Flexible hours

    edison%20scientific

    San Francisco, CA
    7 days ago
  • $140k - $200k

     ...Member Of Technical Staff San Francisco Bay Area Shape...  ...the critical infrastructure that powers breakthrough...  ...high-quality training data at scale...  ...is a hands-on engineering role. You'll write...  ...the broader RL tooling ecosystem...  ...AI data company, ML platform company... 
    Training
    Immediate start
    Flexible hours

    Labelbox

    San Francisco, CA
    3 days ago
  • $240k - $350k

    Machine Learning Engineer Edison Scientific builds...  ...chemistry, and AI. Role As a Member of Technical Staff, Machine Learning...  ...in which to train and deploy AI agents...  ...including building internal infrastructure to improve the efficiency...  ...of work in applied ML research and... 
    Training
    Full time
    Work at office
    Flexible hours

    Edison Scientific Inc.

    San Francisco, CA
    1 day ago
  • $300k - $400k

     ...frontier AI research company and training our own models end-to-end....  ...are looking for a research engineer to build the data systems and...  ...pipelines for complex, long-horizon RL tasks. Build robust...  ...building the data and environment infrastructure that determine what our... 
    Training
    Full time

    mirendil

    San Francisco, CA
    7 days ago
  • $300k - $400k

     ...frontier AI research company and training our own models end-to-end....  ...are looking for research engineers to help build the post-training stack for...  ..., data, verification, and infrastructure all meet. You will design...  ...: Develop and iterate on RL, SFT, and distillation recipes... 
    Training
    Full time

    mirendil

    San Francisco, CA
    7 days ago
  • $300k - $400k

     ...frontier AI research company and training our own models end-to-end....  ...Role We are looking for engineers to help build the post-training stack for frontier...  ...of research and infrastructure. You will work to push the scale of our RL stack, whether it is novel recipe... 
    Training
    Full time

    mirendil

    San Francisco, CA
    7 days ago
  • $275k

     ...pretraining, domain-specific RL, ultra-long context,...  ...role As a Research Engineer on the Inference & RL...  ...and power large-scale post-training workflows. This...  ...execution and distributed infrastructure. You will work on...  ...issues in production ML systems Ability to... 
    Training
    Full time
    Relocation
    Visa sponsorship

    magic.dev

    San Francisco, CA
    7 days ago
  • $275k

     ...pretraining, domain-specific RL, ultra-long context,...  ...role As a Research Engineer on the RL Research &...  ...This role focuses on post-training: identifying...  ...behavior. You will own the infrastructure and experimental workflows...  ...large-scale data or ML systems Ability to... 
    Training
    Full time
    Relocation
    Visa sponsorship

    magic.dev

    San Francisco, CA
    7 days ago
  •  ...Opportunity You'll join the Pre-Training Data team, which...  ...problem, not an infrastructure problem. You'll work alongside...  ..., ships like an engineer: You build the pipelines...  ...prototypes Solid ML fundamentals: you've trained...  ...both pre-training and post-training Small,... 
    Training
    Weekend work

    Liquid AI

    San Francisco, CA
    1 day ago
  •  ...Opportunity You'll join the Pre-Training Data team, which decides what...  ...a research problem, not an infrastructure problem. You'll work...  ...a researcher, ships like an engineer: You build the pipelines and...  ...traceable. Work with pre-training, post-training and eval teammates to... 
    Training
    Weekend work

    Liquid AI, Inc

    San Francisco, CA
    1 day ago
  •  ...Title: Machine Learning Infrastructure EngineerLocation: San...  ...Learning Infrastructure Engineer to help architect the compute, training, and execution frameworks...  ...with extraordinary technical foundations will be evaluated...  ....OP Recruiting, a member of the Objective Partners... 
    Training
    Full time
    Work at office
    Flexible hours

    Objective Paradigm

    San Francisco, CA
    4 days ago
  •  ...research lab building benchmarks and RL environments to push the frontier of...  ..., 5 days in office Own platform engineering, develop frontier long-horizon RL environments...  ...Build our RL environment training and inference infrastructure to support customer usage at scale.... 
    Training
    Full time
    H1b
    Work at office
    Relocation
    Visa sponsorship

    halluminate

    San Francisco, CA
    7 days ago
  •  ...Member of Technical Staff – Machine Learning I’m partnering with a rapidly scaling...  ...$40M Series A to expand its engineering team. Their AI-powered platform...  ...Work across the full ML lifecycle: from data pipelines, to model training, to deployment Adapt and fine... 
    Training
    Work at office

    Quantix Search

    San Francisco, CA
    4 days ago
  •  ...and operating simulation infrastructure where next-generation models...  ...-impact former founders, ML engineers, roboticists, and data leads...  .... THE ROLE As a Member of Technical Staff, you will work directly with...  ...understanding of evaluations, RL, and how LLMs and Agents... 
    Full time

    abundant

    San Francisco, CA
    7 days ago
  •  ...discovery. We are seeking a Member of Technical Staff, Machine Learning to...  .... You’ll innovate on ML methods, work closely...  ...with chemists and software engineers to integrate models into...  ...and optimize scalable infrastructure for model training, deployment, and monitoring... 
    Training

    Inductive Bio

    San Francisco, CA
    1 day ago
  • $197.3k - $313.7k

     ...Job Category Software Engineering Job Details About...  .... As a Principal Member of Technical Staff (PMTS) / Staff Software...  ...incident response, post-incident remediation...  ...Kubernetes (EKS), and Infrastructure as Code (Terraform)...  ..., benefits, training, assessment of job performance... 
    Training
    Full time

    Salesforce

    San Francisco, CA
    7 days ago
  • $150k - $250k

     ...Job Description You've built RL environments or graders, and hardware engineering doesn't scare you. Be the first ML hire on data nobody else has...  ...CAD and ECAD sessions into training environments, scoring models...  ..., and package them as post-training data for frontier labs... 
    Training
    Full time
    Work at office
    Relocation
    Visa sponsorship

    RnB Consultancy

    San Francisco, CA
    9 days ago
  • $250k

     .... As a Research Engineer you'll own the training pipeline, from data...  ...you'll do Post-train models using...  ...generation, RL environments and...  .../ post-training infrastructure (e.g. Tinker, verl...  ...Academic or industry ML/RL experience;...  ...agency, strong technical acumen and clear... 
    Training
    Full time
    H1b
    Work at office

    General Analysis

    San Francisco, CA
    11 days ago
  •  ...Member of Technical Staff @ Lotus AI Who we are Lotus AI...  ...includes ex-founders and engineers who have built and...  ...work across model training and fine-tuning, model...  ..., and data infrastructure simplification Familiarity...  ...that power AI or ML workflows Hands-on... 
    Training

    Lotus Health AI, Inc

    San Francisco, CA
    21 hours ago
  • $2,000 per month

     ...manufacturing, logistics, collection, and model training to scale the physical labor dataset orders of magnitude...  ...in the world. Job Summary We’re hiring Members of Technical Staff — the general research/engineering seat. If you have a seriously compelling research... 
    Training
    Work at office
    Relocation package

    Build AI

    San Francisco, CA
    15 hours ago
  • $150k - $300k

     ...efficient and economical commerce. We're training robot AGI to power a proprietary...  ...and obsessed team of the world's best engineers and operators. If you are obsessed with...  ...Role Nimble is looking for a Member of Technical Staff to help us advance our robotics moonshot... 
    Training
    Local area
    Immediate start
    Flexible hours
    Weekend work

    Nimble Robotics

    San Francisco, CA
    4 days ago
  •  ...make agents work, from data processing, training, inference, evaluation, to other components...  ...designing, building, and deploying ML systems You can write clean, maintainable...  ..., large datasets, and modern AI serving infrastructure Experience with cloud infrastructure and... 
    Training
    Work at office
    Flexible hours

    Asari AI

    San Francisco, CA
    1 day ago
  • $225k - $275k

     ...for researchers, engineers and organizations...  ...with agents, with RL, with anything...  ...so we're hiring a Member of Technical Staff for Product Engineering...  ...researchers to train models every hour...  ...with enough infrastructure comfort to handle...  ...any exposure to ML training workflows... 
    Training
    16 hours
    Full time
    Live in
    Work at office
    Relocation package
    Night shift

    sf-tensor

    San Francisco, CA
    7 days ago

Do you want to receive more vacancies?

Subscribe and receive similar vacancies to Member of Technical Staff - ML Infrastructure Engineer, RL Post-training. Be the first to apply!