Senior LLM Infrastructure Engineer

Role: Senior LLM Infra Engineer

Location: New York (3 days a week onsite)

Compensation: Up to $400,000 TC

We’re working with a leading AI group pushing the boundaries of large language model infrastructure. We’re looking for Senior LLM Engineers to help design, scale, and optimize training and inference systems that power business-critical applications.

You’ll be building the backbone for high-performance, production-grade LLM workloads across HPC and cloud environments, leveraging specialised hardware and distributed systems to make models faster, more reliable, and more efficient. If you love working at the intersection of large-scale ML, systems optimization, and cutting-edge hardware, you’ll probably enjoy this.

You’ll be

• Building and scaling production LLM systems
• Optimizing workloads across on-prem HPC clusters and cloud platforms
• Profiling, benchmarking, and tuning ML applications for performance and efficiency
• Collaborating with research teams to productionize state-of-the-art models
• Leveraging GPUs, TPUs, and custom accelerators for large-scale training and inference

You should bring

• 4+ years coding using an OO language (Python strongly preferred)
• Experience designing, developing, and supporting ML applications
• Deep understanding of ML model architectures, especially transformers
• Experience profiling, benchmarking, and optimising ML workloads

This is a high-impact, high-autonomy role in a world-class team.