Machine Learning Engineer, Infra, AI for Drug Discovery
Core
Building and operating scalable model-serving infrastructure and lifecycle management platforms for machine learning, scientific, and agentic workloads to enable reliable production deployment.
Role type
Senior IC Machine Learning Infrastructure Engineer
Builds
Model-serving platform, deployment tooling, observability systems, and event-driven integrations for model lifecycle management
Domain
Biotech / Drug Discovery / Cloud Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Python, Cloud systems (AWS), Kubernetes, Containers, IaC (Terraform/Pulumi), CI/CD, Distributed systems, Observability tools
Preferred skills
Model-serving frameworks (KServe, Triton, vLLM), GPU optimization, MLOps platforms, Scientific computing
Technologies
AWS, EKS, EC2, S3, IAM, SQS, SNS, CloudWatch, Kubernetes, Helm, Terraform, Pulumi, Datadog, Prometheus, Grafana, OpenTelemetry
Responsibilities
Design and operate scalable model-serving infrastructure; Evolve internal deployment platform into self-service; Improve platform scalability and reliability; Build observability and operational tooling; Develop validated configuration interfaces and deployment patterns; Converge real-time and batch inference workflows; Contribute to model lifecycle management infrastructure; Build event-driven integrations for model workflows; Define metrics for model cost and quality; Partner with teams to remove infrastructure bottlenecks; Own workstreams from design through production support
Seniority
Senior, hands-on IC