We’re building a world of health around every individual - shaping a more connected, convenient and compassionate health experience. At CVS Health®, you’ll be surrounded by passionate colleagues who care deeply, innovate with purpose, hold ourselves accountable and prioritize safety and quality in everything we do. Join us and be part of something bigger – helping to simplify health care one person, one family and one community at a time.
Principal Machine Learning Engineer Principal / Staff+ Individual Contributor · Personalization & Decisioning Platform
POSITION SUMMARY
Join a leading retail organization's personalization and decisioning platform team at a pivotal moment of building a unified, large-scale machine learning platform that drives one-to-one offer, content, and channel decisions across millions of customers. This is a hands-on, backend-heavy engineering role that you will spend the majority of your time designing and building production systems, not just models. As the most senior engineer on the team, you will set technical direction for how machine learning is designed, built, tested, deployed, and operated at scale. You will architect the backend services, data contracts, and distributed pipelines that let causal inference, reinforcement learning, and large-scale optimization models run reliably in production - and you will raise the engineering bar for everyone around you through code review, design review, and direct mentorship. You will partner closely with data engineering, MLOps, product, and platform teams to ensure models are not just accurate, but maintainable, observable, testable, and safe to change. A meaningful part of this role is technical leadership: setting standards, unblocking other engineers, coaching mid-level and senior ML engineers, and acting as the de facto tech lead for the team's most complex initiatives. Experience in retail, ad-tech, or large-scale marketing/offer personalization is a strong plus.
WHAT YOU'LL DO
Backend Engineering & Systems Design · Architect and build scalable, production-grade backend services (APIs, microservices, batch and streaming pipelines) that serve machine learning decisions to downstream systems with strict latency, throughput, and reliability requirements. · Design data contracts and interfaces between data engineering, model training, and production serving layers, with a focus on training-serving parity and point-in-time correctness. · Own the design of versioned, queryable feature stores and point-in-time lookup APIs that eliminate feature leakage and support both training and real-time inference from a single code path. · Design and optimize large-scale distributed computing workflows (containerized batch jobs, parallelized training, and optimization solves) that run reliably within tight operational SLAs. · Make build-vs-buy and architecture tradeoff decisions (storage formats, orchestration frameworks, solver choice, serving patterns) and document them as durable architectural decisions. Software Development Best Practices · Set and enforce engineering standards across the ML codebase: modular design, dependency management, code review rigor, automated testing (unit, integration, regression), CI/CD, and documentation. · Introduce and champion practices that make ML systems easier to change safely - contract tests between pipeline stages, reproducible environments, infrastructure-as-code, and rollback-safe deployments. · Drive observability and monitoring for both software and model health: service-level metrics, data/feature drift, model calibration, and automated alerting - treating production ML with the same rigor as any other production system. · Lead design and code reviews across the team, balancing pragmatism with long-term maintainability; prevent and resolve technical debt before it becomes a roadblock. Tech Lead & Mentorship · Act as the technical lead for the team's most complex, cross-repo initiatives - breaking down ambiguous problems into phased, de-risked implementation plans. · Mentor and grow mid-level and senior machine learning engineers; provide hands-on guidance on system design, modeling tradeoffs, and production readiness. · Anticipate and prevent problems and roadblocks before they occur, including proactively identifying scaling limits, failure modes, and operational risk in systems under design. · Partner with engineering managers and product leadership to shape team roadmap, estimate complex work, and raise the technical bar org-wide without requiring formal people-management authority. · Communicate complex technical concepts, tradeoffs, and risks clearly to both engineering peers and non-technical business stakeholders. Machine Learning & Optimization · Build and productionize large-scale models and decisioning systems - including causal inference / incrementality models, reinforcement-learning-based policies, and mixed-integer optimization for constrained allocation problems. · Partner with data science to translate research prototypes into reliable, scalable, production-grade systems, closing the gap between notebook and production. · Build and maintain experimentation infrastructure (holdouts, A/B tests, counterfactual validation) and monitoring for incrementality, drift, and model/business performance.
REPRESENTATIVE TECH STACK
The stack below reflects the kind of systems this role works in day to day. Deep expertise in all of these is not required - strong engineering fundamentals and the ability to ramp quickly matter more than prior exposure to any single tool. Languages: Python, SQL ML / Data Libraries: scikit-learn, XGBoost, pandas, NumPy, SciPy Optimization / OR: Gurobi, PuLP, SCIP / COIN-OR solvers for large-scale mixed-integer programming (MIP) Distributed Computing: Dask (including distributed/Kubernetes-backed clusters) for large-scale parallel training and scoring Pipeline Orchestration: Kubeflow Pipelines running on Kubernetes (AKS or equivalent managed Kubernetes) Backend / APIs: Flask-based REST services, SQLAlchemy, containerized microservices Data Platform: Snowflake as the primary data warehouse; cloud object storage (e.g., ADLS/S3/GCS) for model and pipeline I/O Infrastructure: Docker, Kubernetes, CI/CD pipelines (Jenkins / GitHub Actions / GitLab CI), infrastructure-as-code ML Techniques: Causal inference / uplift modeling (meta-learners, causal forests), reinforcement learning for sequential decisioning, gradient-boosted trees, large-scale constrained optimization
REQUIRED QUALIFICATIONS
· 7+ years of progressively complex software, ML, data science/ engineering experience, including 5+ years building and operating production backend systems or data-intensive platforms at scale. · 5+ years building, deploying, and owning machine learning systems in production, with a strong focus on software development best practices (testing, CI/CD, code review, modular design). · Expert-level Python and SQL; deep understanding of software design patterns, API design, and distributed systems fundamentals. · Proven experience architecting scalable, data-intensive backend systems (microservices, REST APIs, batch/streaming pipelines) in a major cloud environment (Azure, AWS, or GCP). · Hands-on experience with containerization and orchestration (Docker, Kubernetes) and with ML/data pipeline orchestration tools (Kubeflow, Airflow, or similar). · Demonstrated experience as a technical lead: setting technical direction, running design/code reviews, and mentoring other engineers. · Strong track record anticipating risk and preventing production issues before they occur, and communicating technical tradeoffs clearly to both engineers and business stakeholders.
PREFERRED QUALIFICATIONS
· Experience with large-scale mathematical/combinatorial optimization (MIP solvers such as Gurobi, PuLP, or SCIP) in a production decisioning system. · Experience with causal inference (uplift modeling, CATE estimation, meta-learners) and/or reinforcement learning applied to real-world decisioning or recommendation problems. · Experience designing versioned feature stores with point-in-time correctness and training-serving parity. · Experience with distributed computing frameworks (Dask, Spark, or Ray) for large-scale data processing and model training. · Experience in retail, ad-tech, or marketing personalization domains. · Demonstrated proficiency across mathematical analysis methods, machine learning, and statistical/predictive modeling, with deep specialization in at least one area (e.g., causal inference, RL, or optimization).
EDUCATION · Bachelor's degree or equivalent work experience in Computer Science, Mathematics, Statistics, Engineering, Business Analytics, Economics, Physics, or a related discipline. · Master's degree preferred, but not required given sufficient hands-on production experience.
Pay Range
The typical pay range for this role is:
$144,200.00 - $288,400.00 This pay range represents the base hourly rate or base annual full-time salary for all positions in the job grade within which this position falls. The actual base salary offer will depend on a variety of factors including experience, education, geography and other relevant factors. This position is eligible for a CVS Health bonus, commission or short-term incentive program in addition to the base pay range listed above. This position also includes an award target in the company’s equity award program.
Our people fuel our future. Our teams reflect the customers, patients, members and communities we serve and we are committed to fostering a workplace where every colleague feels valued and that they belong.
Great benefits for great people
We take pride in offering a comprehensive and competitive mix of pay and benefits that reflects our commitment to our colleagues and their families.
This full‑time position is eligible for a comprehensive benefits package designed to support the physical, emotional, and financial well‑being of colleagues and their families. The benefits for this position include medical, dental, and vision coverage, paid time off, retirement savings options, wellness programs, and other resources, based on eligibility. Additional details about available benefits are provided during the application process and on Benefits Moments.
We anticipate the application window for this opening will close on: 11/29/2026
Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state and local laws.
