About this role
Summary: Design and maintain scalable cloud infrastructure for ML training and inference in computational biology. Architect distributed computing systems, build CI/CD pipelines, and optimize data infrastructure for large-scale biological datasets.
- Design, build, and maintain scalable cloud infrastructure (GCP/AWS) for ML training, inference, and optimization workloads in computational biology
- Train, deploy, and optimize ML model pipelines for protein binding prediction, structure-activity relationship (SAR) modeling, and related tasks
- Architect and manage distributed computing systems (Kubernetes, Docker, Ray, Slurm, or similar) for high-throughput biological data processing
- Build robust CI/CD pipelines and MLOps tooling to support reproducible, auditable scientific workflows
- Leverage AI-assisted development tools (Claude Code, Codex, Gemini) to accelerate engineering velocity across the team
- Collaborate closely with ML engineers and computational scientists to identify and eliminate bottlenecks across the stack
- Manage and optimize data infrastructure for large-scale biological datasets (genomics, proteomics, assay data)
- Contribute to infrastructure-as-code practices using Terraform, Pulumi, or equivalent
- Evaluate and integrate third-party tools and cloud-native services to improve cost efficiency and developer velocity