Senior Machine Learning Engineer

Revelation Pharma LLC•Remote, US,

2d•$155,000 - $185,000

About The Position

The Senior Machine Learning Engineer is responsible for developing and implementing machine learning solutions that enhance clinical decision-making, patient outcomes, and operational efficiency across Evergreen's telehealth platform. This role combines deep technical expertise with healthcare domain knowledge to design, deploy, and optimize production-ready AI systems that are accurate, explainable, and compliant with regulatory requirements. Working closely with Engineering, Clinical Leadership, and Product stakeholders, the Senior Machine Learning Engineer will help translate complex clinical and business challenges into scalable machine learning solutions. The ideal candidate is a hands-on engineer who thrives in a fast-paced startup environment, exercises sound technical judgment, and is passionate about building AI capabilities that deliver measurable value while maintaining the highest standards of patient safety and quality. Note on Scope: The Senior Machine Learning Engineer serves as the technical owner of Evergreen's machine learning and predictive analytics capabilities. This role is responsible for designing, deploying, monitoring, and continuously improving the models that power clinical decision support, patient risk stratification, adherence forecasting, dosage optimization, and agent-driven workflows. Working closely with Engineering, Clinical Leadership, and Product stakeholders, the Senior Machine Learning Engineer ensures that AI systems are scalable, explainable, compliant, and aligned with patient safety requirements. The role influences machine learning architecture, model governance, and technical standards while serving as a key contributor to Evergreen's long-term AI strategy.

Requirements

Applied Machine Learning (Expert): Proven experience building, training, and deploying production ML models (classification, regression, and time-series forecasting). Strong foundation in statistical modeling, experimental design, and A/B testing.
Production ML / MLOps (Expert): Hands-on experience deploying and maintaining ML systems in production, including model versioning, monitoring, drift detection, retraining pipelines, and CI/CD for ML workflows.
Healthcare ML / High-Stakes Modeling (Strong): Experience building models in regulated or high-stakes environments (healthcare, biotech, clinical, or financial systems), including safety, explainability, and validation requirements.
LLM & NLP Systems (Strong): Experience with LLM-based applications including RAG architecture, embeddings, prompt engineering, evaluation frameworks, and hallucination mitigation in production systems.
AWS ML Stack (Strong): Experience with key AWS services such as SageMaker, Bedrock, Amazon Forecast, and S3-based data pipelines. Ability to design and operate end-to-end ML systems in AWS.
Data & Feature Engineering (Strong): Experience building scalable feature pipelines and working with complex datasets, ideally including healthcare or structured medical data (FHIR or equivalent). Strong SQL and data modeling skills.
Model Evaluation & Safety Design (Strong): Ability to design evaluation frameworks for ML systems where accuracy alone is insufficient—must include calibration, confidence thresholds, and safe failure modes.
MS or PhD in a quantitative discipline: Math, Econometrics, Physics, Computational Engineering, or a related field
Excellent Python skills, with production experience in a modern ML framework such as PyTorch or TensorFlow
Experience developing and deploying production ML models, not just research or notebooks
Experience building statistical or neural network models for prediction, classification, or state-transition problems
Experience with MLOps: model versioning, automated retraining, drift detection, and production monitoring

Nice To Haves

Experience developing ML models in a healthcare, clinical, biotech, or pharma context
Experience with structured clinical data, including FHIR, claims, or EHR data
Experience building explainable models for regulated or safety-sensitive domains
Published research, patents, or an advanced thesis involving applied statistical or computational modeling

Responsibilities

Design, training, validation, and monitoring of the core predictive and state-transition models powering the clinical product
Production ML pipelines and retraining cadence, including drift detection and rollback
Model explainability and validation work needed to support clinical and regulatory review
Build the evaluation and validation framework for all agent-driven clinical recommendations, including safety guardrails, confidence thresholds, and human-in-the-loop escalation triggers for the Clinical Protocol Agent
Develop patient risk stratification models for adherence prediction, adverse event likelihood, dosage titration optimization, and churn/dropout risk using clinical, behavioral, and engagement signals
Design predictive models that support clinical decision-making while maintaining explainability and regulatory compliance
Collaborate with clinical stakeholders to translate protocols, treatment pathways, and pharmacy domain expertise into model features, training labels, and validation criteria
Implement and manage the predictive analytics pipeline on AWS, including Amazon Forecast (DeepAR+) for time-series clinical predictions, S3 Vectors for embedding-based patient similarity and retrieval, and Bedrock for agent inference
Design and build the RAG architecture that grounds agent responses in clinical protocols, formulary data, and operational knowledge sources
Contribute to machine learning architecture decisions and establish technical standards that support scalability, reliability, and maintainability
Partner with Engineering leadership to evaluate emerging AI technologies and recommend solutions aligned with business objectives and patient safety requirements
Own model lifecycle management, including training pipelines, feature stores, model versioning, A/B testing, drift detection, and retraining triggers in production
Establish model monitoring and alerting, including prediction quality dashboards, distribution shift detection, and automated alerts when performance degrades below established thresholds
Build explainability layers for clinical recommendations to support provider trust, auditability, and regulatory requirements
Ensure machine learning systems meet governance, compliance, and documentation standards appropriate for healthcare environments
Serve as a senior technical resource for AI and machine learning initiatives across the organization
Provide technical guidance and mentorship to engineers contributing to machine learning, AI, and analytics initiatives
Partner with Clinical Leadership, Engineering, Product, and Operations teams to ensure models deliver measurable business and patient outcomes
Work with DevOps/AgentOps resources to ensure all ML decisions are logged, reproducible, and auditable for regulatory review