Staff Engineer, ML Infrastructure & Compute Platform

Odyssey; Greater London; On-site; GBP 60,000 - 80,000; Full time

Job summary

Odyssey is looking for an engineer in Greater London. You will develop the low-latency model inference platform and scale core data processing infrastructure. This role requires strong programming skills in Python or Go, and experience with Docker and Kubernetes.

The ideal candidate is motivated by building for the future of AI, with a collaborative mindset and excellent communication abilities. Experience in managing large-scale systems with GPU workloads is essential for this groundbreaking work.

Qualifications

• Motivated by building for the frontier in AI technologies.
• Deep experience with containerization and orchestration.
• Proven track record in large-scale GPU computational systems.

Responsibilities

• Develop and operate low-latency model inference platform.
• Engineer and scale core data processing infrastructure.
• Design and maintain GPU-based training clusters.
• Automate infrastructure provisioning and monitoring.
• Drive performance tuning and cost optimization.
• Collaborate with researchers to optimize workflows.

Skills

Strong programming skills (Python, Go)

Experience with Docker and Kubernetes

Building and managing distributed systems

Infrastructure as Code (Terraform)

Collaboration and communication skills

Job description

Odyssey is looking for an engineer in Greater London. You will develop the low-latency model inference platform and scale core data processing infrastructure. This role requires strong programming skills in Python or Go, and experience with Docker and Kubernetes.

The ideal candidate is motivated by building for the future of AI, with a collaborative mindset and excellent communication abilities. Experience in managing large-scale systems with GPU workloads is essential for this groundbreaking work.