Machine Learning Infrastructure Engineer, AI for Drug Discovery

About the role

Roche's AI for Drug Discovery (AI4DD) group, Prescient Design, builds the machine learning platforms that let researchers and engineers move models from experimentation into reliable scientific and production workflows. As Machine Learning Infrastructure Engineer, you will help build and operate the platforms that support model deployment, evaluation, promotion, monitoring and lifecycle management. The role covers model-serving platforms, real-time and batch inference, GPU-backed services, agentic applications and in-silico drug discovery workflows.

Key responsibilities

• Design, implement, ship and operate scalable model-serving infrastructure for ML, scientific, LLM and agentic workloads.
• Evolve the internal model deployment platform into a reliable, self-service platform for teams across the organization.
• Improve scalability and reliability, including scale-to-zero, faster model startup, workload isolation, traffic management and reduced request failures and latency.
• Build observability and operational tooling for model usage, latency, reliability, resource consumption, inference cost and service-level indicators.
• Develop validated configuration interfaces, reusable deployment patterns, APIs, command-line tools and documentation.
• Contribute to model lifecycle management, including registration, versioning, evaluation, promotion, release gates, monitoring, environment progression and rollback.
• Build event-driven integrations connecting model publication, evaluation, promotion, deployment and retraining.
• Partner with ML, data, scientific and platform teams to turn requirements into maintainable solutions and remove infrastructure bottlenecks.

Required profile

• BS or MS in Computer Science, Engineering or a related field, or equivalent practical experience.
• 3+ years of experience in software engineering, infrastructure, platform, DevOps, MLOps or a related area.
• Experience designing, deploying or operating cloud systems, preferably on AWS (EKS, EC2, S3, IAM, SQS, SNS, CloudWatch).
• Experience with containers, Kubernetes, Helm and IaC tools such as Terraform or Pulumi.
• Experience with CI/CD, Git workflows, automated testing and software releases.
• Ability to troubleshoot complex systems using metrics, logs, traces and observability tools.
• Understanding of distributed-systems concepts such as concurrency, queuing, retries, timeouts, idempotency and backpressure.
• Preferred: familiarity with model-serving frameworks (KServe, Triton, vLLM, Ray Serve, Prefect, Dagster), model registries, MLOps platforms, event-driven systems, model evaluation and drift monitoring, and experience supporting scientific computing or distributed training.

What we offer

• Expected salary range of $147,600-$274,000 depending on location, experience and qualifications; a discretionary annual bonus may be available.
• The position qualifies for the benefits described in the original listing.
• Relocation benefits are not available.