Research Engineer — Frontier AI Inference Systems

Prime Intellect, Inc.; United States; On-site; USD 150,000 - 350,000; Full time

Benefits offered by this job

Remote work option

Office SF

Visa sponsorship

Relocation assistance

Team off-sites

Learning opportunities

Job summary

Prime Intellect, Inc. is building the open frontier AI platform and RL inference systems for cutting-edge research and production use. We seek engineers to scale 1-3T parameter models on NVL72 clusters, improving throughput and enabling frequent model updates.

You will extend vLLM integrations, optimize multi-node inference, and work with researchers to balance model quality against deployment cost on frontier hardware. Remote or in-person options available.

Qualifications

• Experience building or optimizing GPU inference systems.
• 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.

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.

Skills

GPU inference systems

Python

PyTorch

Performance profiling

ML systems debugging

Job description

Prime Intellect, Inc. is building the open frontier AI platform and RL inference systems for cutting-edge research and production use. We seek engineers to scale 1-3T parameter models on NVL72 clusters, improving throughput and enabling frequent model updates.

You will extend vLLM integrations, optimize multi-node inference, and work with researchers to balance model quality against deployment cost on frontier hardware. Remote or in-person options available.