Location: United States

About the Company

We are a fast-growing AI company building next-generation large language models at scale. Our mission is to bring powerful, reliable AI systems into production environments used by thousands of customers. We value technical excellence, deep collaboration, and engineers who thrive on solving real-world problems at scale.

Role Overview

We are seeking a Staff / Principal ML Infrastructure Engineer to lead the design, deployment, and scaling of our large language model infrastructure. This role sits at the intersection of machine learning, systems engineering, and platform design, enabling teams to train, serve, and monitor models efficiently and reliably.

This is not a prompt engineering role – it is focused on building robust, production-grade ML infrastructure and operational pipelines.

Responsibilities

• Design, implement, and maintain high-performance infrastructure for training and serving LLMs
• Optimize model pipelines for efficiency, latency, and cost at scale
• Collaborate with ML researchers, platform engineers, and product teams to deploy models safely into production
• Build monitoring, alerting, and tooling to ensure reliability and observability of large-scale ML systems
• Evaluate and integrate new frameworks, tools, and architectures to improve ML workflows
• Provide technical leadership and mentorship to other engineers on the team

Qualifications

• 7+ years of software engineering experience, including 3+ years building production ML systems
• Deep experience with distributed training and inference frameworks (e.g., PyTorch, JAX, TensorFlow)
• Familiarity with model serving technologies and orchestration (e.g., Triton, Ray, Kubernetes)
• Strong understanding of GPU/TPU infrastructure, performance optimization, and scalability challenges
• Proven experience solving reliability, latency, and cost trade-offs in production ML systems
• Excellent collaboration, communication, and problem-solving skills
• Experience mentoring or leading engineering teams is a plus

Why You’ll Enjoy This Role

• Work on cutting-edge LLM infrastructure at scale
• Influence the design of systems that power real-world AI applications
• Collaborate with some of the most talented engineers in AI
• Flexible work arrangements and competitive compensation

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

Reece Waldon