Responsibilities Design and build REST APIs and web applications for cloud services and on-site device configuration, monitoring, and management Develop intuitive management UIs for both cloud-based workflows and local hardware deployment Architect backend services that bridge cloud (AWS) and on-premises AI compute environments Design low-latency database schemas covering job tracking, results storage, audit logging, and device management Build and maintain containerized AI inference pipelines deployed on both cloud and dedicated GPU hardware Implement end-to-end observability (telemetry, logging, alerting) across distributed environments Identify and resolve performance bottlenecks in inference pipelines and large binary data workflows Ensure software meets regulatory compliance standards (FDA 21 CFR Part 11/820, SOC2) Partner closely with ML Engineering and Research teams to bring models into production Contribute to design reviews, architecture discussions, and incident response rotations Produce technical documentation for API specs, deployment guides, and regulatory submissions Requirements Bachelor's degree or higher in Computer Science, Engineering, Mathematics, or equivalent 5–7 years of professional software development experience 4+ years building and operating REST APIs and backend services in production 3+ years in AI/ML application development, including deploying and optimizing inference services 4+ years with Python and TypeScript/JavaScript across backend and frontend 3+ years with AWS (EC2, S3, EKS, ECR, Lambda, CloudWatch) 3+ years with Docker and Kubernetes, including edge or on-prem deployments 3+ years with SQL and NoSQL database design 2+ years developing software in regulated environments (FDA and/or SOC2) Experience with observability tooling (Prometheus, Grafana, DataDog, or similar) Strong grasp of DevOps practices and CI/CD pipelines Frontend experience with React or similar frameworks Comfort with ambiguity and a bias toward shipping in a startup environment. #J-18808-Ljbffr
