Senior LLM Infrastructure & RL Integration Engineer (Hybrid Cloud & AI Serving)

Prime Intellect • United State

Remote Visa Sponsorship Relocation

Apply Now

AI Summary

Build and optimize scalable LLM serving infrastructure and integrate RL systems at Prime Intellect, a frontier AI startup. Design multi-tenant GPU-aware scheduling, inference optimization frameworks, and resilient distributed serving platforms. Requires 3+ years in large-scale ML systems, deep inference backend expertise, and full-stack debugging skills.

Key Highlights

Hybrid role bridging LLM serving, inference optimization, and RL integration at frontier AI scale

Design multi-tenant GPU-aware scheduling, autoscaling, and failover for cloud GPU fleets

Optimize inference frameworks (vLLM, SGLang, TensorRT-LLM) and RL stack integration

Key Responsibilities

Build a multi-tenant LLM serving platform across cloud GPU fleets with GPU-aware scheduling and failover capabilities

Optimize inference frameworks (vLLM, SGLang, TensorRT-LLM) for tensor/pipeline/expert parallelism, quantization, and speculative decoding

Integrate distributed inference systems into Prime Intellect’s RL training stack for end-to-end performance optimization

Design autoscaling, routing, and load-balancing solutions to meet SLOs for latency and throughput

Develop reproducible performance suites and CI/CD pipelines with artifact promotion and performance gates

Implement observability (metrics, logs, tracing) and structured incident response for resilient infrastructure

Looking to advance your Devops career with relocation support? Explore Devops Jobs with Relocation Packages that include comprehensive packages to help you move and settle in your new role.

Technical Skills Required

Distributed Systems & Kubernetes Large-Scale LLM Inference GPU-Aware Scheduling & Optimization

Benefits & Perks

Cash compensation range of $150,000–$300,000 with significant equity incentives

Full visa sponsorship and relocation support

Flexible work arrangement (remote or San Francisco office)

Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.

Nice to Have

Kernel-level optimization with CUDA/Triton and Nsight profiling

Rust or C++ for systems performance languages

Open-source contributions to serving, inference, or RL infrastructure projects

Job Description

Prime Intellect is building the open superintelligence stack: the infrastructure frontier AI labs build internally, made available to every ambitious AI team.

Want the full job description? Read the complete details on LinkedIn, the original posting.

Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.