Sr. Engineer, AI Platform
The Sr AI Platform Infrastructure Engineer is a pivotal position for driving the strategic vision and technical execution for the Cancer Diagnostics AI/ML platform. The role is accountable for the architecture, reliability, scalability, security and cost of every layer beneath the platform's applications, from the cloud, network and compute foundation to the serving, orchestration and streaming systems that workloads run on.
- Madison, Wisconsin, United States
- Full-time
- On-site
- $99K–$199K per year
- Posted Nov 11, 2026
INDUSTRYHealthcareAllied Health & Therapy
Responsibilities
- Design and own the platform's cloud and Kubernetes foundation, including account and network topology, VPC and subnet design, private connectivity, ingress and egress control, DNS and certificates, and the provisioning, upgrade, migration, multi-tenant isolation and security of production clusters.
- Lead the platform's expansion across clusters and regions, covering topology, identity federation, state and data placement, traffic management and failure domains, and evaluate multi-cloud where business need warrants it.
- Own infrastructure-as-code and GitOps for the platform, including module design, state management, environment promotion, drift control, and the testing and rollback of infrastructure changes; build and operate the CI/CD and deployment tooling that platform software releases run on in partnership with the AI Platform Software lead.
- Architect, build and operate production model serving and GPU infrastructure for large language and predictive models, including scheduling, multi-tenancy, autoscaling, low-latency serving, inference optimization (quantization, batching, graph compilation), and capacity planning and cost attribution for shared compute.
- Partner with the AI Platform Software and Safety leads on the model lifecycle by providing the infrastructure it runs on, including reproducible data, feature and training pipelines with dataset-to-model lineage, promotion environments, the traffic-shifting and rollback mechanisms behind canary, shadow and A/B rollout, and pipeline enforcement of the evaluation and promotion gates.
- Architect, build and operate workflow orchestration and event-streaming infrastructure, including workflow and state-machine design, event-driven triggers and scheduling, retries and idempotency, topic and partition design, schema management, delivery semantics and cross-region replication.
- Own the observability stack and service level objectives for infrastructure services, with proactive detection across the platform; lead disaster-recovery strategy as a business tradeoff between cost and recovery time and recovery point objectives; and serve as the escalation point for complex infrastructure incidents, leading the post-incident analysis that drives systemic reliability improvements.
- Own infrastructure security and governance, including least-privilege identity, secrets management, network policy, workload isolation and auditability, and partner with the safety lead to build the governance controls into the paved road as automated checks.
- Design, develop, test, review and deploy production software as a hands-on contributor, mentor engineers, and represent the infrastructure pillar in design reviews and long-term technology planning.
Requirements
- Bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field
- Experience in a Cancer Diagnostics
Nice to have: Go, Rust, Multi-cloud experience, Knative, KEDA, Service mesh, API gateway, Zero-trust network patterns, FinOps
Skills
Benefits
- Equal Opportunity Employer of Minorities/Women/Individuals with Disabilities/Protected Veterans
More jobs nearby
Full description
Company details are for members
Sign up for a free job alert to see Abbott Laboratories's profile, website and LinkedIn, and the same for every employer on Referso Jobs.