Lead Software Engineer (Inference Platform), London

Your Impact

We are building the largest foundation models in biotech and applying them immediately to cure disease. You will play a pivotal role in ensuring the reliability and scalability of the foundations that make this possible.

As a Principal Engineer, you will lead the efforts to harden our systems, ensuring our groundbreaking AI is built on an unshakeable base, working closely with the research team and the Applied ML teams to ensure the infrastructure is stable, reliable and can operate with more data and larger models as we grow. 

What You Will Do

• 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.

Skills and Qualifications

Essential:

• Proven experience in architecting and managing large-scale AI/ML workloads in a production environment.
• Expertise in cloud compute design, specifically within Google Cloud Platform (GCP).
• Orchestration: Significant experience deploying and managing complex workloads within Kubernetes (GKE).
• 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.