Location: United States (West Coast preferred, remote considered)

About the Company

We are a rapidly growing AI company delivering large language models at scale. Our mission is to ensure models not only perform well in research but also serve real-world applications reliably and efficiently. We are looking for engineers who enjoy solving high-scale inference and systems challenges.

Role Overview

We are seeking a Senior / Staff LLM Systems Engineer to lead the development, optimization, and deployment of large language model inference pipelines. This role focuses on high-throughput, low-latency serving and production reliability, bridging ML research and platform engineering.

This is not a training-focused role – the emphasis is on serving models at scale, optimizing systems, and enabling production ML reliability.

Responsibilities

• Design, implement, and optimize inference pipelines for large language models
• Improve throughput and latency of model serving in production environments
• Collaborate closely with infrastructure, platform, and ML research teams to ensure smooth deployment
• Build monitoring, observability, and alerting systems for inference performance and reliability
• Identify and solve scaling challenges across GPUs, TPUs, or distributed environments
• Evaluate and adopt new technologies, frameworks, and architectures to improve inference efficiency
• Mentor other engineers and contribute to technical strategy for production ML systems

Qualifications

• 5+ years of software engineering experience, including hands-on ML systems experience
• Strong background in distributed systems, performance tuning, and low-latency architectures
• Experience with model serving frameworks (e.g., Triton, vLLM, Ray, TorchServe)
• Familiarity with GPU/TPU infrastructure, multi-node deployment, and system-level optimization
• Understanding of ML workloads and trade-offs between accuracy, latency, and cost
• Proven ability to deliver production-grade ML systems at scale
• Excellent collaboration and problem-solving skills

Why You’ll Enjoy This Role

• Work on cutting-edge LLM inference systems at scale
• Solve technically challenging, high-impact engineering problems
• Collaborate with top ML researchers and platform engineers
• Competitive compensation and flexible work arrangements

Darwin Recruitment is acting as an Employment Agency in relation to this vacancy.

Reece Waldon