Data Scientist

Hybrid onsite Tuesday Wednesday and Thursday



Data Scientist / Machine Learning Engineer
Position Overview
As a Data Scientist / Machine Learning Engineer on our AI Builder program, you will design, develop, and operationalize advanced analytics and machine learning solutions focused on anomaly detection, pattern recognition, predictive modeling, and intelligent monitoring across large, complex healthcare and operational datasets. You?ll identify meaningful patterns, emerging signals, and behavioral shifts that inform enterprise decisions and improve operational processes.
This role also plays an important part in moving data science solutions from experimentation into production. You?ll collaborate with engineering, architecture, and business teams to build reliable pipelines, automated model workflows, and integrations between analytical solutions and enterprise systems ? applying statistical rigor and modern MLOps practices in equal measure.
Key Accountabilities
Design, develop, and maintain anomaly detection and pattern recognition systems across large-scale healthcare and operational datasets, using techniques such as clustering, classification, time-series analysis, change-point detection, and graph-based analytics.
Develop reusable feature engineering, scoring, and analytical components that support multiple enterprise use cases rather than isolated point solutions.
Apply natural language processing, large language models, and other machine-learning techniques to unstructured and semi-structured data to surface patterns, themes, and emerging signals.
Design and contribute to production-grade machine learning pipelines, including automated data preparation, feature generation, training, validation, deployment, scoring, and monitoring.
Develop and maintain CI/CD workflows for data science solutions, including source control, automated testing, model versioning, and rollback capabilities.
Establish monitoring for production analytical systems ? model performance, data quality, feature drift, model drift, and pipeline health.
Partner with engineering and technology teams to integrate models and services with enterprise applications, APIs, and downstream business processes.
Communicate analytical findings, model behavior, and limitations clearly to both technical and non-technical stakeholders.
Candidate Profile
The successful candidate can independently solve complex analytical problems and move solutions beyond exploratory analysis into reliable, integrated production systems. You have a strong foundation in statistics and machine learning, with genuine interest in anomaly detection, pattern recognition, and finding meaningful signal in large, messy datasets. You understand that good data science requires more than model development, and you?re comfortable partnering with engineers on deployment, automation, and operational support.
Required Qualifications
Strong professional experience in Data Science, Machine Learning, advanced analytics, statistical modeling, or a related discipline.
Strong hands-on programming capability in Python.
Strong SQL skills and experience working with large relational or analytical datasets.
Strong foundation in statistics, machine learning, model evaluation, and experimental design.
Experience developing real-world models using techniques such as classification, clustering, anomaly detection, predictive modeling, time-series analysis, or related approaches.
Experience with data preparation, feature engineering, target construction, validation, and model performance evaluation.
Experience developing reusable and maintainable analytical code rather than exclusively notebook-based or ad hoc analysis.
Experience helping move machine-learning or advanced-analytics solutions into production.
Understanding of model scoring, deployment, monitoring, data quality, model drift, and production lifecycle considerations.
Ability to work effectively when requirements, data, or solution approaches are incomplete or evolving.
Ability to communicate analytical methodology, findings, limitations, and business implications clearly.
Preferred Qualifications
Healthcare, payer, claims, payment-integrity, provider, member, clinical, financial, or other regulated-data experience.
Hands-on experience developing anomaly-detection or emerging-pattern systems.
Experience with supervised, semi-supervised, and unsupervised machine-learning techniques.
Experience with advanced modeling approaches such as gradient boosting, ensemble methods, deep learning, graph-based methods, sequence models, or representation learning.
Experience with model explainability, calibration, threshold optimization, and false-positive reduction.
Experience with Snowflake and Azure.
Experience working within containerized Data Science environments.
Familiarity with production ML and MLOps practices such as model registries, versioning, CI/CD, experiment tracking, monitoring, and lifecycle management.
Experience integrating analytical models into APIs, applications, decision systems, or enterprise workflows.
Experience working across Data Engineering, Software Engineering, MLOps, Platform, and Cloud teams.
Experience applying NLP, embeddings, or GenAI where unstructured information must be converted into structured data or incorporated into a broader analytical solution.
Experience mentoring other Data Scientists, helping establish modeling standards, or guiding analytical design decisions.
Example Focus Areas
Builders on this team are currently supporting high-priority initiatives such as:
Claims: identifying anomalies, outliers, and emerging patterns to improve payment integrity and fraud detection.
Customer Service: analytics on interactions, transcripts, and workflow data to surface emerging issues and improve lifecycle tracking.
Technology: pattern and anomaly analysis across systems, logs, and tickets to improve technology efficiency.
Ways of Working
Comfortable operating with incomplete or evolving requirements, without heavy day-to-day direction.
Delivers useful, working increments quickly (think agile, two-week delivery cycles) and iterates based on feedback.
Takes ownership from problem definition through production operation.
Has access to the Company?s enterprise AI toolset (including an internal enterprise ChatGPT-based knowledge platform and Codex/GPT access) and is expected to use it effectively.


Benefits:

York Solutions Offers a generous benefits package for eligible full-time employees:

• BCBS Medical with 3 Plans to choose from (PPO and High deductible PPO plans with Health Savings Program)
  
• Delta Dental plan with 2 free cleanings and insurance discounts
  
• Eye Med Vision with annual check-ups and discounts on lens
  
• Life and Accidental Death Insurance paid by company
  
• John Hancock 401(k) Retirement Plan with discretionary company match
  
• Voluntary Insurance programs such as: Hospital Indemnity, Identity Protection, Legal Insurance, Long Term Care, and Pet Insurance.
  
• Flexible work environment with some remote working opportunities
  
• Strong fun and teamwork environment
  
• Learning, development, and career growth