LLM Inference Engineer
LLM Inference Engineer
LLM Inference Engineer
Periodic Labs
Periodic Labs is an AI and physical sciences lab focused on building advanced models for scientific discoveries. The LLM Inference Engineer role involves integrating and optimizing large-scale inference systems to support AI research, working with cutting-edge technologies and contributing to open-source software.
Qualification
- Experience optimizing inference for large open-source models.
- Familiarity with high-performance model serving frameworks like TensorRT-LLM, vLLM, SGLang.
- Knowledge of distributed inference techniques such as tensor/expert/pipeline parallelism.
- Experience with speculative decoding and KV cache management.
- Ability to optimize GPU utilization and latency for reinforcement learning.
Responsibility
- Integrate, optimize, and operate large-scale inference systems for AI scientific research.
- Build and maintain high-performance serving infrastructure for large language models.
- Deliver low-latency, high-throughput access to models across thousands of GPUs.
- Collaborate with researchers and engineers on large-scale reinforcement learning workloads.
- Support frontier-scale experiments and contribute to open-source LLM inference software.
