Machine Learning Engineer, Infra, AI for Drug Discovery

Genentech's AI for Drug Discovery group is seeking a Machine Learning Infrastructure Engineer to build and operate the model-serving platforms that power ML, LLM, and agentic workflows in drug discovery. The role focuses on designing and maintaining scalable inference infrastructure, model lifecycle management, observability, and self-service deployment tools. You'll partner with scientists and engineers to move models from experimentation into reliable production workflows.

• Design, implement, ship, and operate scalable model-serving infrastructure for machine learning, scientific, LLM, and agentic workloads.
• Evolve the internal model deployment platform into a reliable, self-service platform for teams across the organization.
• Improve platform scalability and reliability including scale-to-zero, faster model startup, workload isolation, traffic management, and latency reduction.
• Build observability and operational tooling for model usage, latency, reliability, resource consumption, and cost.
• Improve usability of model deployment via validated configuration interfaces, APIs, CLI tools, and documentation.
• Converge real-time and batch inference workflows onto shared platform capabilities.
• Contribute to model lifecycle management including registration, versioning, evaluation, promotion, monitoring, and rollback.
• Build event-driven integrations and consistent metrics for model cost, quality, and reliability.
• Partner with ML, data, scientific, and platform teams to translate requirements into maintainable solutions and own workstreams end-to-end.