Staff Software Engineer (Inference Platform), London

Requirements

• Proven experience in architecting and managing large-scale AI/ML workloads in a production environment.
• Orchestration: Significant experience deploying and managing complex workloads within Kubernetes (GKE).
• Expertise in cloud compute design, specifically within Google Cloud Platform (GCP).
• Professional familiarity with NVIDIA GPU generations and the intricacies of high-performance compute.
• Strong programming skills and a "reliability-first" approach to software development.

Nice to Have

• A career history that spans both ML Software Engineering and Infrastructure SRE roles.
• Experience leading multi-disciplinary projects and navigating complex stakeholder requirements in a fast-paced environment.
• Familiarity with workload scheduling, ML efficiency research, and hardware benchmarking.
• Experience with Google TPU generations and specialized ML-driven R&D cycles.

What You'll Be Doing

• Develop and operate our inference platform, serving fleets of cutting-edge machine learning models to scientific applications.
• Design strategy and build roadmaps for maturing the platform.
• Architect and optimize our next-generation inference services. You will solve core scaling limits, ensuring high-throughput performance and feature parity across our model serving stack.
• Contribute to core technical decisions on tooling and architectural design while partnering with science, product, and operations teams to align infrastructure with biotech R&D cycles.
• Deliver high-quality and well-tested user-focused features.

Perks and Benefits

• Hybrid working model - required to be in the office 3 days a week.
• Diverse and collaborative culture.
• Equal employment opportunities.
• Supportive environment for every employee.
• Commitment to accommodating additional needs.