Research Engineer, RL Frontiers

Etched • San Jose, CA

2d • $400,000 • Onsite

About The Position

Etched is building AI systems that accelerate their own development. The Research Engineer on the RL Frontiers team trains proprietary frontier models to automate kernel development, ASIC engineering, production pipelines, and 3-D hardware operating systems. The role uses proprietary simulators and environments to create custom data mixes and post-train models to state-of-the-art performance on difficult engineering tasks.

The position owns the post-training stack end to end and builds reinforcement-learning environments with ASIC, kernel, and supercomputing engineers. Environments are rewarded using simulation, formal tools, tests, and hardware measurements. The role also develops custom data mixes and benchmarks that improve model productivity while avoiding reward hacking.

Etched is a fully in-person team in San Jose (Santana Row). The company values engineering skills, has no boundary between engineering and research, and expects technical staff to contribute across both areas and disciplines as needed.

Requirements

• Hands-on post-training experience, including supervised fine-tuning (SFT) and reinforcement learning such as PPO or GRPO.
• Have shipped models that people used.
• Experience taking a model from poor to good performance on a task it was not built for; scarce-data experience is especially relevant.
• Strong PyTorch and distributed-training engineering skills.
• Read model rollouts and check results before trusting them.
• Understand the systems side of RL well enough to make the training loop faster and cheaper.
• Entrepreneurial judgment and ability to make good decisions under compute and data constraints.

Nice To Haves

• Experience as an early post-training hire at an applied AI company.
• Former founder.
• Experience with RL or post-training frameworks such as verl, OpenRLHF, TRL, or prime-rl, or inference engines such as vLLM or SGLang.
• Experience with agentic, multi-turn RL with verifiable rewards.
• Experience with distillation and training small, specialized models for production.
• Experience in ASIC design or verification, accelerator kernels, or large-scale compute infrastructure.

Responsibilities

• Own the post-training stack end to end.
• Build RL environments with ASIC, kernel, and supercomputing engineers, using rewards from simulation, formal tools, tests, and hardware measurements.
• Create custom data mixes that unlock frontier performance on relevant tasks.
• Create benchmarks that drive real productivity in models and avoid reward hacking.
• Contribute to both engineering and research and work across disciplines as needed.

Benefits

• Medical, dental, and vision packages with generous premium coverage.
• $500 per month credit for waiving medical benefits.
• Housing subsidy of $2,500 per month for those living within walking distance of the office.
• Relocation support for those moving to San Jose (Santana Row).
• Wellness benefits covering fitness, mental health, and more.
• Daily lunch and dinner in the office.
• Unlimited compute budget subject to ROI justification.
• Base compensation of $400K+ plus significant equity.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed