# Research Engineer - Inference at Primeintellect

- Company: Primeintellect
- What the company does: Train, deploy, and continuously improve your own models on an integrated compute, training, inference, and sandbox stack. Backed by Menlo.
- Company website: https://www.primeintellect.ai/
- Type: Startups (AI role)
- Level: Mid level
- Location: San Francisco
- Work setup: On-site
- Posted: 2026-10-16
- Apply by: 2026-11-30
- Apply: https://jobs.ashbyhq.com/PrimeIntellect/3103e1a4-2515-4ae0-a2f0-784e25d30cfe?utm_source=1752vc&utm_medium=careers
- Page: https://www.1752.vc/careers/jobs/primeintellect-research-engineer-inference/

## About the role

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. Found on 1752vc Careers, the job board for startup and VC roles.

## What they're looking for

- 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

Tags: Research

Source: 1752vc Careers, https://www.1752.vc/careers/jobs/primeintellect-research-engineer-inference/