Research Engineer - Inference
Prime Intellect · San Francisco · Remote
Infrastructureremote$150k–$350k
At a glance
Highlights
- Build inference systems powering RL research scaling to 1–3T parameter models.
- Improve rollout throughput for long-horizon agents with growing contexts.
- Make frequent model updates practical with fast trainer-to-inference transfers.
What they offer
- Equity incentives
- Flexible work arrangements - remote or in-person in San Francisco
- Visa sponsorship and relocation assistance
- Quarterly team off-sites, hackathons, conferences and learning opportunities
Ideal candidate
A systems-minded engineer obsessed with inference performance who thrives turning profiles into real speedups to power frontier open-source RL research.
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
- remote policy
- Remote optional
- visa sponsorship
- Visa sponsorship and relocation assistance available
Lab profile
About Prime Intellect
Building the open superintelligence stack for post-training frontier AI at scale
What they build
- Lab platform
- Compute and environments
- Evaluations
Known for
- Post-training at frontier scale
- SFT and RL
- Tool use and agent workflows
- High-performance training infrastructure
Posted · Last seen