Machine Learning Engineer, Infra, AI for Drug Discovery

Responsibilities: Design, implement, ship, and operate scalable model-serving infrastructure for ML, scientific, LLM, and agentic workloads Advance internal deployment platform into a reliable self-service platform for teams across the organization Improve scalability and reliability (scale-to-zero, faster startup, workload isolation, traffic management, latency reduction) Build observability and tooling for usage, latency, reliability, and cost metrics Enhance usability of deployment via validated interfaces, APIs, and documentation Unify real-time and batch inference workflows on shared platform capabilities Oversee model lifecycle infrastructure (registration, versioning, promotion, monitoring, rollback) Develop event-driven integrations linking publication, evaluation, promotion, deployment, and retraining workflows Create metrics and signals for cost, quality, reliability, and fitness for downstream workflows Collaborate with ML, data, scientific, and platform teams to remove bottlenecks and translate requirements Own workstreams from design to production support with strong software-engineering practices

Key requirements: BS or MS in Computer Science, Engineering, or related field, or equivalent practical experience 3+ years in software/infra/platform/DevOps/MLOps or related area Strong Python programming and production software delivery experience Experience designing, deploying, or operating cloud systems (preferably AWS) with EKS, EC2, S3, IAM, SQS, SNS, CloudWatch Experience with containers, Kubernetes, Helm, and IaC tools (Terraform or Pulumi) Experience with CI/CD, Git workflows, automated testing, and software release practices Ability to troubleshoot complex systems using metrics, logs, traces, and observability tools (Datadog, Prometheus, Grafana, OpenTelemetry) Understanding of distributed-systems concepts (concurrency, queuing, timeouts, retries, idempotency, backpressure, failure recovery) Ability to gather requirements, communicate tradeoffs, and document systems for varied users Demonstrated ability to deliver practical, incremental solutions independently Collaborative mindset Strong communication of technical tradeoffs Problem-solving mindset Python production software engineering AWS cloud services (EKS, EC2, S3, IAM, SQS, SNS, CloudWatch) Kubernetes, Helm, IaC (Terraform, Pulumi)