Carex is partnering with a biotech industry partner to identify a Senior AI Platform Infrastructure Engineer to lead the architecture, development, and operation of a scalable, secure, and reliable AI/ML platform supporting cancer diagnostics. This hands-on technical leadership role is responsible for the cloud and Kubernetes foundation, GPU infrastructure, model serving, workflow orchestration, infrastructure automation, and platform observability. The engineer will collaborate with AI Platform Software and Safety leads to deliver robust infrastructure that supports the full machine learning lifecycle while balancing performance, security, reliability, and cost.
Location: Madison, WI
What You’ll Do
- Architect, build, and maintain the platform’s cloud infrastructure and Kubernetes foundation, including network topology, private connectivity, cluster provisioning, upgrades, security, and multi-tenant isolation.
- Lead platform expansion across clusters and regions, addressing identity federation, data placement, traffic management, failure domains, and multi-cloud strategies as needed.
- Own infrastructure-as-code and GitOps practices, including reusable modules, state management, environment promotion, drift detection, testing, and rollback strategies.
- Build and operate CI/CD pipelines and deployment tooling in collaboration with the AI Platform Software lead.
- Design and operate production model-serving and GPU infrastructure for large language models and predictive models, including scheduling, autoscaling, low-latency inference, performance optimization, capacity planning, and cost attribution.
- Partner with AI Platform Software and Safety leads to support reproducible data, feature, and training pipelines; dataset-to-model lineage; promotion environments; controlled rollouts; and automated evaluation and deployment gates.
- Architect and operate workflow orchestration and event-streaming systems, including scheduling, event-driven triggers, retries, idempotency, schema management, delivery guarantees, and cross-region replication.
- Establish infrastructure observability, service-level objectives, proactive monitoring, and disaster-recovery strategies aligned with business requirements for recovery time, recovery point, and cost.
- Serve as an escalation point for complex infrastructure incidents and lead post-incident reviews to drive systemic reliability improvements.
- Own infrastructure security and governance, including identity and access management, secrets management, network policies, workload isolation, auditability, and automated compliance controls.
- Contribute directly to production software development through design, coding, testing, code reviews, and deployment.
- Mentor engineers, represent the infrastructure function in technical design reviews, and contribute to long-term technology planning.
- Promote accountability, innovation, integrity, quality, teamwork, inclusion, and reliable execution.
What You’ll Bring
- Bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
- Demonstrated expertise designing and deploying AI solutions that deliver measurable business impact.
- Strong understanding of ethical considerations in AI systems.
- At least three years of project leadership experience, including Agile project management and Scaled Agile Frameworks (SAFe).
- Advanced proficiency with machine learning frameworks, Python, and cloud platforms.
- Strong analytical, troubleshooting, and problem-solving skills, with expertise in AI/ML techniques.
- Production software development experience with Python, Go, and/or Rust.
- Experience leading platform transformations and/or building large-scale AI infrastructure.
- Experience with multi-cloud environments or migrating significant workloads between cloud providers.
- Knowledge of Kubernetes-native serverless technologies and event-driven autoscaling, such as Knative or KEDA, as well as service meshes, API gateways, and zero-trust networking patterns.
- Experience managing GPU infrastructure costs or comparable FinOps responsibilities for shared compute environments.
- Ability to operate effectively within enterprise governance and compliance requirements, including environments where network, identity, and change management are managed by separate teams.
- Familiarity with compliance frameworks and regulated environments, such as HIPAA, FDA, and GxP.
- Experience guiding cross-functional engineering teams and mentoring senior-level engineers.
- Strong technical leadership, collaboration, communication, and ownership skills.
Carex Consulting Group is an equal opportunity employer. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, marital status, disability, gender identity, or Veteran status.
#LI-LL1