Senior Engineer, Machine Learning

Virta Health

2d • $161,500 - $232,500 • Remote

About The Position

As a Senior Engineer, Machine Learning on Virta Health’s Applied AI team, you will build and deploy models that help personalize care for members, including identifying who may need a coach’s attention, which interventions may be effective, and how a member’s health is changing. You will turn ambiguous clinical and operational questions into well-defined modeling tasks, establish honest baselines, and deliver models to production.

You will develop models using Virta’s longitudinal member data and build model-specific logic on the ML platform to support retraining, quality monitoring, and detection of drift or anomalies. You will work with Product Engineering to put model outputs in front of members and care teams, with ML Ops on production infrastructure, with clinicians to interpret data, and with Product Analytics on experiments and causal analysis. The role includes predictive modeling, causal ML, experimentation, evaluation, error analysis, and ML- and GenAI-derived signals for personalized experiences. You will also lead complex initiatives and share practices that improve model quality and delivery across teams.

Virta is a remote-first company with office hubs in Denver and San Francisco. The role may involve access to sensitive patient information governed by HIPAA, and employees are expected to follow security and privacy procedures; training is provided. Virta uses AI-powered tools in certain parts of its recruiting process, while final hiring decisions are made by Virta personnel.

Requirements

• At least 5 years building, evaluating, and deploying production-grade machine-learning systems for real-world use cases.
• Strong foundation in traditional machine learning, including predictive modeling, tree-based models such as XGBoost, and time-series analysis on structured longitudinal data.
• Rigorous evaluation and experimental-design skills, including statistical reasoning, offline and online evaluation, and identifying leakage, selection bias, and confounding in messy real-world data.
• Ability to clearly explain model behavior, tradeoffs, uncertainty, and limitations to technical and non-technical stakeholders.
• Experience designing and analyzing experiments to determine what drives an outcome rather than merely correlating with it.
• Depth in one or more of causal ML and experimentation, recommendation or ranking systems, predictive modeling, or NLP/LLM-based systems.
• Responsible use of AI-assisted development to meaningfully accelerate and improve model development.
• Ability to follow Virta’s security and privacy procedures when handling sensitive patient information governed by HIPAA.

Nice To Haves

• Background in clinical or health-tech machine learning, including claims, EHR, clinical notes, scheduling, utilization, or member engagement data.
• Experience with PHI, HIPAA-aware systems, or other regulated data.
• Judgment about when traditional machine learning outperforms LLMs and when an LLM is appropriate.

Responsibilities

• Turn ambiguous clinical and operational questions into well-scoped machine-learning tasks and build strong baselines before adding complexity.
• Build predictive models for member care, such as identifying disengagement risk, members likely to benefit from coach outreach, and changes in members’ health; partner with Product Engineering to deliver model signals to members and care teams.
• Build model-specific production logic on the ML platform, including retraining triggers, drift and anomaly detection, and continuous evaluation, with compliance considerations incorporated from the start.
• Design offline and online evaluations, select metrics suited to imbalanced, delayed, and noisy healthcare outcomes, and conduct careful error analysis.
• Build causal models validated against clinical experiments and partner with Product Analytics on variance-reduction techniques such as CUPED and CUPAC.
• Build ML- and GenAI-derived signals for product squads to use in personalized coaching and member experiences.
• Lead complex ML initiatives from problem framing through production, coordinating technical decisions and dependencies across Applied AI, ML Ops, Product Engineering, and Product Analytics.
• Share knowledge and practices that strengthen model quality and delivery across the team.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed