LLM Inference Engineer

Periodic Labs • Menlo Park, CA

90d

About The Position

You will integrate, optimize, and operate large-scale inference systems to power AI scientific research. You will build and maintain high-performance serving infrastructure that delivers low-latency, high-throughput access to large language models across thousands of GPUs. You will work closely with researchers and engineers to integrate cutting-edge inference into large-scale reinforcement learning workloads. You will build tools and directly support frontier-scale experiments to make Periodic Labs the world’s best AI + science lab. You will make contributions to open-source LLM inference software.

Requirements

• Experience optimizing inference for the largest open-source models.
• Familiarity with high-performance model serving frameworks such as TensorRT-LLM, vLLM, SGLang.
• Knowledge of distributed inference techniques including tensor/expert/pipeline parallelism, speculative decoding, and KV cache management.
• Experience optimizing GPU utilization and latency for reinforcement learning.

Responsibilities

• Integrate, optimize, and operate large-scale inference systems.
• Build and maintain high-performance serving infrastructure for large language models.
• Deliver low-latency, high-throughput access to models across thousands of GPUs.
• Work closely with researchers and engineers on large-scale reinforcement learning workloads.
• Build tools to support frontier-scale experiments.
• Contribute to open-source LLM inference software.

What This Job Offers