Remote · US only jobs

Research Engineer - Inference

Prime IntellectRemote · US onlyFull-timeSponsors US visasPosted 1 month ago

$150k–$350k/yr listed by the employer

Looks real. 1 thing to check before you apply.

On Prime Intellect’s own careers site (Ashby), checked open today.

  • To check: Wide pay range: top of the range is 2.33× the bottomAsk what the job pays at your level before you interview.
  • Checked: On the company's own careers siteAshby board
  • Checked: Checked open todayAshby board
  • Checked: Pay listedJob posting
  • Checked: No reposts foundAshby board
  • Trust score 89 / 100 · Looks good
See all 6 checksShow fewer
How we check

What you’ll do

  • Extend prime-rl’s vLLM integration to support new model architectures in RL training, validating at small scale before larger runs.
  • Improve rollout throughput for long-horizon agents by tuning concurrency and KV-cache reuse as context lengths grow.
  • Optimize multi-node MoE inference, including expert parallelism and prefill/decode separation.
  • Reduce trainer-to-inference weight-update overhead while keeping rollout workers on the intended policy version; evaluate lower-precision inference and its effects on RL training.

Summarised from the posting by AI and can be wrong. The full description is the source.

Requirements

Experience

  • Experience building or optimizing GPU inference systems, with an understanding of inference-engine internals
  • Experience debugging numerical or integration issues in ML systems
  • Contributions to vLLM or another inference engine (preferred)

Skills

  • Strong Python skills and experience with PyTorch or a comparable ML framework
  • Ability to profile end-to-end workloads and turn measurements into verified performance improvements
  • CUDA or Triton kernel work, particularly for low-precision inference (preferred)

Your match

Sign in and add your resume to see which of this job's requirements it shows.

Sign in to check your match

Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.

Benefits

Health insurance
Full medical coverage for employees and dependents
Dental & vision
Full dental and vision coverage for employees and dependents
Paid time off
Flexible PTO
Equity
Equity incentives
Learning & tuition
Professional development budget for courses and conferences; quarterly team off-sites, hackathons, conferences, and learning opportunities
Wellness & mental health
$200/month health and wellness benefit
Flexible schedule
Flexible work arrangements, with the option to work remotely or in person at the San Francisco offices
Meals
Company-covered meals when working from the San Francisco office
Relocation help
Relocation assistance for international candidates
Other
Cash compensation range of $150,000–$350,000, including equity incentives, Visa sponsorship for international candidates

Full job description

From Prime Intellect’s careers site

OWN YOUR INTELLIGENCE

Prime Intellect is building the open superintelligence stack: the infrastructure frontier AI labs build internally, made available to every ambitious AI team.

Show full descriptionShow less

Our platform, Lab, unifies compute, environments, evaluations, secure sandboxes, high-performance training, and deployment into one full-stack system for post-training at frontier scale - from SFT and RL to tool use, agent workflows, and continuously improving production models. We are building open frontier AI: open-source models trained end to end for long-horizon tasks like autonomous research, and the full-stack platform our own research team uses to build them. The next generation of AI companies, enterprises, and research teams do not just need more GPUs. They need the ability to turn their own workflows, tools, data, and feedback loops into superintelligence they own.

Prime Intellect has raised $150M in total funding from Founders Fund, Radical Ventures, NVIDIA, and exceptional AI, infrastructure, and enterprise operators, including Andrej Karpathy, Dwarkesh Patel, and leaders and founders from Ramp, Perplexity, Harvey, Mercor, Zapier, Datadog, Cognition, OpenAI, Thinking Machines, Together AI, SemiAnalysis, LangChain, Browserbase, Cloudflare, Sierra, Databricks, Airbnb, OpenRouter, Standard Intelligence, Fleet, Core Auto, and more. We are looking for people who want to build at the intersection of frontier research, real infrastructure, and go-to-market for a category that does not fully exist yet.

ROLE IMPACT

Build the inference systems that power Prime Intellect’s RL research, scaling toward 1–3T parameter models on NVL72 clusters. Your work will improve rollout throughput and make frequent model updates practical.

RESPONSIBILITIES

  • Extend prime-rl’s vLLM integration to bring new model architectures into RL training, with small-scale validation before larger runs.
  • Improve rollout throughput for long-horizon agents, tuning concurrency and KV-cache reuse as context lengths grow.
  • Optimize multi-node MoE inference, including expert parallelism and the tradeoffs of separating prefill from decode.
  • Reduce trainer-to-inference weight-update overhead through sharding-aware transfer and communication overlap, while keeping rollout workers on the intended policy version.
  • Build on FP8 and evaluate lower precision. Use trainer/sampler mismatch checks to catch numerical regressions and measure the effect on RL training.
  • Work with model researchers on architecture choices that improve inference efficiency, balancing model quality against execution cost on the target hardware.

REQUIREMENTS

  • Experience building or optimizing GPU inference systems, with an understanding of inference-engine internals.
  • Strong Python skills and experience with PyTorch or a comparable ML framework.
  • Ability to profile end-to-end workloads and turn measurements into verified performance improvements.
  • Experience debugging numerical or integration issues in ML systems.

Nice to have

  • Contributions to vLLM or another inference engine.
  • CUDA or Triton kernel work, particularly for low-precision inference.

WORK ARRANGEMENT

  • Flexible work arrangements, with the option to work remotely or in-person at our offices in San Francisco.

BENEFITS AND PERKS

  • Cash Compensation Range of $150-350k, including equity incentives, aligning your success with the growth and impact of Prime Intellect.
  • Full medical, dental and vision coverage for employees and dependents.
  • Flexible PTO.
  • $200/month health and wellness benefit.
  • Visa sponsorship and relocation assistance for international candidates.
  • Professional development budget for courses and conferences.
  • Quarterly team off-sites, hackathons, conferences and learning opportunities.
  • Company-covered meals when working from our San Francisco office.

If you're excited about the opportunity to build the foundation for the future of decentralized AI and create a platform that empowers developers and researchers to push the boundaries of what's possible, we'd love to hear from you.

Something wrong with this job? Report it · This flag looks wrong

Similar jobs

See more like this