Lead Software Engineer (Inference Platform), London
Core
Architecting and operating large-scale inference platforms to serve fleets of cutting-edge AI/ML models for drug discovery and scientific applications.
Role type
Principal Software Engineer (Inference Platform)
Builds
High-throughput, reliable model serving infrastructure for biotech R&D
Domain
Biotechnology / AI Infrastructure / Cloud Computing
Deliverable
infrastructure
Required skills
Large-scale AI/ML workload architecture, Google Cloud Platform (GCP) expertise, Kubernetes (GKE) orchestration, NVIDIA GPU high-performance compute management, Production software development with reliability focus
Preferred skills
ML Software Engineering and Infrastructure SRE crossover, Multi-disciplinary project leadership, Workload scheduling, ML efficiency research, Hardware benchmarking, Google TPU experience
Technologies
Google Cloud Platform, Kubernetes, NVIDIA GPUs, Google TPUs
Responsibilities
Develop and operate the inference platform serving ML model fleets, Design strategy and build roadmaps for platform maturation, Architect and optimize next-generation inference services to solve scaling limits, Contribute to core technical decisions on tooling and architecture, Partner with science and product teams to align infrastructure with R&D cycles
Seniority
Principal, hands-on IC with strategic leadership