Machine Learning Engineer

What Interwell Health offers

This remote role focuses on meaningful, real world impact in healthcare. You will own the full lifecycle of machine learning initiatives, from data preparation and model building to deployment, monitoring, and ongoing optimization. Work alongside engineers, product managers, and clinicians to develop new ML products and enhance existing systems, with opportunities to tackle traditional ML and large language model based capabilities in a collaborative, cross functional environment.

Responsibilities

• Develop and deliver end to end machine learning solutions, defining technical requirements, architecting scalable systems, and implementing monitoring, logging, and maintenance workflows.
• Collaborate closely with engineers, product managers, clinicians, and cross functional partners to build new ML products and enhance existing systems.
• Lead the design and implementation of MLOps frameworks, including pipeline development, CI/CD integration, drift detection, retraining workflows, and rollback strategies.
• Monitor model performance in production, identify issues, propose remediation steps, and ensure strong test coverage and system reliability.
• Apply contemporary software engineering practices to deliver scalable, secure, and maintainable AI/ML systems.
• Develop and tailor API integrations to enable seamless connectivity between cloud based systems and ML services.
• Participate in architectural discussions to ensure ML platforms meet compliance, performance, and scalability standards.

Requirements

• Bachelor's degree in Computer Science, Data Analytics, Software/Computer Engineering, Computational Statistics, Mathematics, or a related discipline.
• Minimum 2 years of professional ML experience, with 3+ years of end-to-end ML development in production (data prep, feature engineering, modeling, calibration, deployment, monitoring, maintenance).
• 3+ years of MLOps experience building production pipelines (CI/CD, model registry, feature store), implementing monitoring and drift detection, and automating retraining.
• 3+ years of Python for production ML (testing, packaging, type hints, linting) and SQL for analytical and production workloads; Scala is a plus.
• 2+ years working with distributed compute and cloud ML environments (for example Spark/Databricks on Azure, AWS, or GCP) and modern data ecosystems (data lakes, DBMS).
• Strong debugging and optimization skills across data and ML workflows.
• Track record of ownership and problem solving—driving measurable impact and quality under ambiguity and evolving requirements.
• Ability to communicate technical decisions clearly and contribute to documentation and design discussions.
• Demonstrated system design and architecture skills for scalable, high performance ML services and batch plus streaming workflows; familiarity with API design and service integration patterns.
• Proven understanding of tradeoffs in latency, cost, performance, and compliance.

Technologies

• Python
• SQL
• Scala
• Spark
• Databricks
• Azure
• AWS
• GCP

Preferred

• 1+ years of Databricks experience plus some experience in infrastructure or networking
• 1+ years implementing LLM based solutions in production, including prompt/response design, evaluation frameworks, guardrails and safety, latency and cost optimization
• 1+ years designing compliant ML platforms (HIPAA, SOC 2) and working with PHI/PII governance, access controls, and auditability