Senior AI Scientis/ ML Engineer

About The Role
You will join a strategic healthcare technology engagement supporting a global medical technology enterprise.
You will own work from problem formulation and experimentation through production implementation, collaborating with data engineers, AI specialists, and MLOps engineers to build reliable, explainable, and scalable solutions on AWS.
Responsibilities
Lead the scientific design and implementation of forecasting and optimization solutions for medication inventory management
Develop medication diversion detection models using behavioral analytics, anomaly detection, risk scoring, and explainable ML techniques
Translate complex clinical and operational needs into clearly defined ML problems with measurable success criteria
Apply classical statistical methods, mathematical optimization, machine learning, and deep learning to forecasting and decision-making challenges
Design rigorous experiments, including temporally appropriate data splits, baselines, ablation studies, calibration, and uncertainty quantification
Build production-ready training pipelines, inference services, batch workloads, and data integrations using AWS-native services
Collaborate with data engineers on feature engineering, dataset preparation, and reproducible data pipelines
Partner with MLOps engineers on deployment, monitoring, drift detection, continuous evaluation, and rollback
Write clean, modular, well-tested Python code and contribute to engineering standards, code reviews, and CI/CD practices
Use AI-assisted coding tools responsibly, validating generated code for correctness, security, and licensing compliance
Document methodologies, assumptions, validation results, architecture decisions, runbooks, and model cards in Confluence
Mentor engineers and junior scientists, communicating technical findings to engineering, clinical, and executive stakeholders
Requirements
A master’s degree in Machine Learning, Statistics, Operations Research, Applied Mathematics, Computer Science, or a related field; a PhD is an advantage
At least 5 years of experience in ML or software engineering, including hands-on modeling and ownership of production ML solutions
At least 3 years of experience building ML services on AWS using native infrastructure and services rather than SageMaker as the primary ML platform
Deep expertise in time-series analysis and forecasting, including classical, machine learning, deep learning, and hierarchical or multi-series approaches
Strong knowledge of mathematical optimization, including linear, mixed-integer, convex, and stochastic methods, and their integration with ML predictions
Excellent Python skills and practical experience with NumPy, pandas, scikit-learn, statsmodels, and PyTorch or JAX
Experience with forecasting frameworks such as Prophet, GluonTS, or Nixtla
Strong AWS expertise, including EKS, S3, IAM, Lambda, EventBridge, ECR, CloudWatch, and Step Functions
Practical experience with Docker, Kubernetes, GitHub Actions, and CI/CD, supported by strong testing, packaging, and observability practices
A proven ability to move models from research prototypes into reliable production services
Experience working in Agile/Scrum teams and maintaining technical documentation in Confluence
Strong written and spoken English, with the ability to explain complex methodologies to technical and business audiences
Experience in healthcare, pharmacy, supply chain, or regulated environments is an advantage
Familiarity with causal inference, counterfactual evaluation, time-series foundation models, experiment tracking, model registries, or inference optimization is an advantage
SoftServe is an equal opportunity employer. Qualified applicants will receive consideration regardless of race, color, ancestry, ethnicity, national origin, religion, sex, sexual orientation, gender identity or expression, age, citizenship, disability, health condition, marital or family status, veteran status, or any other characteristic protected by applicable law.

Work arrangement
Yes