Software Engineer, Data & ML Infrastructure

Surgeon Decision Intelligence is an AI-driven medical imaging company focused on improving orthopedic care through quantitative imaging biomarkers and machine learning. The company is seeking a Software Engineer to build and maintain the data and infrastructure backbone of its AI/ML platform, including databases, data pipelines, APIs, cloud infrastructure, CI/CD, and ML workflow tooling.

Responsibilities:

• Develop and maintain our PostgreSQL database layer: schema changes, SQLAlchemy ORM models, Alembic migrations, and data-integrity constraints
• Build and maintain data ingestion, validation, and ETL pipelines for clinical outcomes data and medical imaging metadata (DICOM)
• Contribute to internal FastAPI services, including endpoints for imaging metadata, annotations, and access control
• Support our Azure cloud infrastructure: blob storage for imaging studies, containerized service deployments, and authentication/authorization workflows
• Help migrate legacy research code into versioned, dependency-managed Python packages following team engineering standards
• Write and maintain CI/CD pipelines, tests, and developer tooling that keep the codebase reliable and reproducible
• Build supporting tooling for ML workflows: dataset extraction and export, experiment/artifact tracking support, and data provenance
• Participate in code review and contribute to team engineering standards and documentation

Requirements:

• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience
• 3+ years of professional software development experience with Python
• Solid working knowledge of SQL and relational databases (PostgreSQL preferred), including schema design and query optimization
• Experience with software development lifecycle practices such as version control, testing, CI/CD, and collaborative development workflows
• Experience with data and ML infrastructure (e.g., data pipelines, feature stores, model deployment, containerization, orchestration frameworks)
• Experience with cloud-based ML pipelines (Azure) and infrastructure-as-code tools
• Proficiency with Git and collaborative development workflows (branching, pull requests, code review)
• Experience writing tested, documented, production-quality code with type hints and modern Python packaging practices
• Strong communication skills and comfort working in a small, fast-moving team
• Remote (U.S.) temporarily, but able to transition to in-person work in New York City in about 6 months
• Experience with an ORM and database migration tooling (e.g., SQLAlchemy and Alembic)
• Experience building REST APIs with FastAPI or a similar Python web framework
• Experience with Azure (blob storage, container apps, Entra ID) or another major cloud platform
• Familiarity with Docker and CI/CD systems (e.g., GitHub Actions)
• Experience with healthcare data: DICOM, medical imaging pipelines, clinical registries, or EHR-derived datasets
• Understanding of HIPAA and handling PHI in production systems
• Familiarity with ML engineering tooling (e.g., MLflow, model/data versioning) and supporting ML teams, even without direct modeling experience
• Experience with modern Python dependency management (e.g., uv, Poetry) and publishing internal packages
• Experience working in or migrating legacy codebases toward better structure and standards
• Experience with software quality practices for regulated medical software, including requirements traceability, validation, configuration management, and controlled releases
• Experience with orchestration or workflow systems for data/ML pipelines, specifically Databricks