SECTION I · THE BRIEF
Brief #90254Updated 19 NOV 2026PALO ALTO, CAAshby
Employbl Company Profile

Member of Technical Staff, RL Infrastructure

AI lab building self-improving AI systems for enterprises that keep learning from each company's own data and workflows.

Location
Palo Alto, CA
Company size
—
Posted
Today
Via
Ashby
Section II · Full ProfileFree with an account
  • 01Comp band & equity packageLocked
  • 02Seniority & experience requirementsLocked
  • 03Interview process & rubricLocked
  • 04Headcount & which departments are hiringLocked
  • 05Growth trajectory in this roleLocked
  • 06Offer & decision timelineLocked

Free · 2 minutes · the funding and stack behind this role

Member of Technical Staff, RL Infrastructure

Noeri· Palo Alto; ZurichView company profile


Job title
Member of Technical Staff, RL Infrastructure
Job location
Palo Alto; Zurich
Job description

About Us
We are a small team of researchers and engineers focused on pushing the frontier of what agents are capable of. We believe the next leap in agent performance will come not from bigger general models, but from specialization and continual learning: agents that get better at their specific job the more they do it. We build the systems that make this possible, turning real-world usage into lasting improvement.

Summary
We are looking for a senior engineer to design and own the systems behind our reinforcement learning stack. You will build the infrastructure that runs rollouts and trains models, across large GPU clusters and for days at a time. This role sits between research and systems engineering. You will work closely with researchers to make RL training fast, stable, and easy to use. You will have a large influence on our technical direction.

Responsibilities

  • Design, build, and maintain our end-to-end RL training system, including rollout generation, reward and verifier services, policy updates, and evaluation.

  • Build scalable, fault-tolerant infrastructure that keeps long training runs healthy without manual intervention.

  • Build systems that turn production usage and feedback into training signal for ongoing model updates.

  • Improve throughput and GPU utilization across training and inference, including asynchronous training setups.

  • Integrate inference engines (such as vLLM or SGLang) into the training loop and optimize them for RL workloads.

  • Build sandboxed environments where agents can run code, use tools, and complete multi-step tasks at scale.

  • Debug hard problems across the stack: numerical instability, scaling bottlenecks, orchestration failures, and hardware faults.

  • Build monitoring, logging, and tooling so researchers can see what is happening in a run and act quickly.

  • Work with researchers on system and algorithm co-design, turning new ideas into production-ready training code.

  • Set engineering standards and mentor other engineers as the team grows.

Qualifications

  • Hands-on experience building and running large-scale ML training or inference systems.

  • Deep experience with distributed systems and training large models across many GPUs.

  • Strong Python skills. C++ or CUDA is a plus.

  • Hands-on experience with PyTorch and distributed training frameworks such as FSDP, DeepSpeed, Megatron-LM, or Ray.

  • Solid understanding of RL workflows for language models and agents, including rollouts, rewards, policy updates, and evaluation.

  • Experience with parallelism strategies, GPU performance tuning, and profiling.

  • A strong debugging instinct and high attention to detail.

  • Comfortable with ambiguity and able to own large problems end to end.

Nice to Have

  • Experience building RL infrastructure at a frontier lab or AI infrastructure company.

  • Contributions to open-source RL or training frameworks.

  • Experience with Kubernetes, Slurm, or other cluster schedulers at scale.

  • Experience with agent environments, code execution sandboxes, or continual learning systems.

 
View job listing ↗
The Employbl newsletter

Get the Employbl newsletter

Which tech companies raised, who is hiring, and what the live dataset says. Sent when there's something worth sending.

Free. Unsubscribe with one click, from any issue.

Funding rounds