Lead Machine Learning Engineer – Action; NBA Platform

Position: Lead Machine Learning Engineer – Next Best Action (NBA) Platform
Location: Columbia

Become a part of our caring community and help us put health first

We are seeking a Lead Machine Learning Engineer to architect, develop, and manage machine learning systems that enable real‑time, personalized decision‑making across digital and assisted channels. These platforms leverage predictive modeling, optimization algorithms, and contextual data to identify the most relevant next action for each individual—at scale, with minimal latency, and with a strong emphasis on reliability and explainability.

This position centers on production machine learning engineering. You will lead the creation of ML pipelines, online inference services, and decision‑time scoring logic, utilizing AI‑assisted and agentic solutions to enhance development velocity, model quality, and operational effectiveness.

Key Responsibilities ML System Design & Architecture

• Design and manage end‑to‑end machine learning systems, including:
• Feature engineering and reuse strategies
• Offline training pipelines
• Online inference and scoring services
• Model versioning, rollout, and rollback procedures
• Ensure systems meet stringent requirements for latency, scalability, reliability, and correctness in real‑time contexts.
• Define clear separation between model development, deployment, and downstream decision logic.

Decision‑Focused Modeling

• Build and operationalize models such as:
• Propensity or likelihood prediction
• Uplift or incremental impact models
• Engagement or responsiveness scoring
• Design models to be composable, explainable, and robust for automated decision workflows.
• Collaborate with analytics and product teams to translate business objectives into measurable modeling outcomes.

AI‑Enabled & Agentic Efficiency

• Apply AI‑assisted and agentic approaches to boost ML engineering productivity, including:
• Automated code generation and refactoring for pipelines and services
• Feature exploration and validation
• Intelligent experiment tracking and comparison
• Enhanced debugging and root‑cause analysis
• Assess and adopt modern tools to accelerate experimentation, reduce manual overhead, and ensure reliable model operations.
• Focus on implementing practical, production‑ready AI tools.

MLOps & Model Operations

• Develop and sustain robust MLOps practices, including:
• Continuous training and deployment pipelines
• Online model monitoring for latency, drift, and stability
• Safe rollout strategies (e.g., canary, shadow, phased releases)
• Fallback mechanisms for model degradation or unavailability
• Guarantee model outputs are traceable, reproducible, and auditable.

Collaboration & Leadership

• Serve as the technical leader for ML engineering, establishing standards and best practices.
• Partner with software engineers, data engineers, and platform teams to ensure seamless integration of ML systems into production.
• Mentor machine learning engineers and contribute to the overall maturity of engineering teams.
• Influence architectural decisions to ensure testability, observability, and resilience.

Role Significance

As reliance on automated and intelligent decisions increases, the integrity of machine learning engineering becomes critical to organizational trust, performance, and user experience. This role ensures that machine learning systems are not only accurate but also reliable, interpretable, and efficient to develop and maintain.

Use your skills to make an impact

Required Qualifications

• 8+ years of experience in machine learning engineering, applied ML, or data‑driven platform development
• 3+ years in a technical lead or senior ML engineering capacity
• Deep expertise in:
• Feature engineering and data pipelines
• Model training and evaluation
• Real‑time or near‑real‑time inference systems
• Strong software engineering skills in Python, Java, or similar languages
• Practical experience with AI‑assisted development tools to streamline ML workflows

Preferred Qualifications

• Experience with personalization, recommendation, or decisioning platforms
• Familiarity with distributed systems and event‑driven architectures
• Experience deploying models in regulated or high‑reliability settings
• Knowledge of model explainability and fairness methodologies

Success Criteria

• Models deliver reliable performance in real‑time decisioning…