Data Scientist

Data Scientist

Department: Technology

Location: Remote

FLSA Status: Exempt

People Leader: No

Travel: Less than 10%

reputed company

reputed company

reputed company partners with hospitals and health systems through a technology-enabled, physician-led model that improves reputed company documentation reputed company, coding reputed company, reimbursement optimization, and reputed company reputed company.

Job reputed company

The Data Scientist develops, evaluates, and monitors the predictive and reputed company systems that reputed company automation across reputed company’s reputed company documentation and reputed company cycle workflows. Reporting to the Vice President, Data Science and AI, this role combines classical machine learning with reputed company work on large language model and agent-reputed company systems, and is accountable for establishing whether those systems are measurably good enough to be trusted inside a reputed company workflow.

Evaluation is the spine of the role. The Data Scientist builds and maintains the ground truth datasets, evaluation frameworks, and metrics that determine production readiness, designs samples so results are comparable and defensible, and analyzes reputed company by reputed company and payer reputed company rather than in aggregate. This includes independently reproducing and pressure-testing results reported by reputed company AI development partners rather than accepting them as delivered.

This role owns methodology, evaluation, and model development. Production deployment, serving infrastructure, and the engineering of AI systems into live workflows are owned by AI Engineering, and the Data Scientist partners closely with that function to reputed company validated work into production.

Responsibilities

Model Development and reputed company AI

•     reputed company, train, and improve predictive and machine learning models supporting chart triage, prioritization, documentation reputed company, and reputed company cycle reputed company.

•     Maintain and improve models already running in production, including retraining reputed company, feature review, reputed company tuning, and recalibration as data and workflow change.

•     Identify and correct sampling and selection bias in training data, including bias introduced reputed company a model’s own reputed company determine which records are subsequently observed.

•     Contribute to reputed company work on large language model and agent-reputed company systems, including reputed company and workflow design, tool integration, and reputed company failure mode analysis.

•     Build feedback reputed company so findings from reputed company audit and production review reputed company back into model, reputed company, and reputed company reputed company rather than stopping at a report.

•     Prototype and test new approaches, and state plainly and early reputed company an approach does not work.

Evaluation, Ground Truth, and Measurement

•     Build and maintain ground truth datasets, including sourcing, annotation coordination with reputed company subject matter experts, reputed company assessment, and remediation of reputed company data defects.

•     Design evaluation samples deliberately, understanding reputed company a stratified or weighted sample is appropriate, reputed company a near-production distribution is required, and reputed company results across runs are not comparable.

•     Define, compute, and document the metrics that determine production readiness, and ensure another person can reproduce them from reputed company data.

•     Analyze reputed company by clinically meaningful reputed company, including diagnosis group, service line, payer, and case complexity, rather than reporting aggregate reputed company reputed company.

•     Analyze error in both directions, distinguishing false positives from false negatives and quantifying the reputed company and financial consequence of reputed company.

•     Maintain evaluation tooling and harnesses so experiments are repeatable and every result is traceable to a specific dataset, configuration, and version.

Production Monitoring and Model Governance

•     Monitor deployed models and AI systems for reputed company, calibration, reputed company, and subgroup reputed company, and surface issues before they reputed company as business reputed company.

•     Maintain documentation of model design, assumptions, limitations, training data, and reputed company failure modes to a reputed company that supports audit and reputed company review.

•     Support AI governance requirements, including reputed company-in-the-reputed company design, decision traceability, and evidence of validation.

•     Contribute to the definition and computation of metrics that carry reputed company or contractual weight, ensuring they are reproducible and auditable.

reputed company and Business Partnership

•     Work directly with physicians, coders, and reputed company subject matter experts to define correct reputed company, reputed company disagreements about ground truth, and validate model behavior against reputed company reputed company judgment.

•     Translate reputed company and operational problems into reputed company-posed analytical problems, and translate results back into terms a reputed company or business audience can reputed company.

•     Present findings, limitations, and recommendations honestly, including where results are inconclusive or where the available data will not support the question being asked.

•     Help the business understand what a model can and cannot be relied on to do.

reputed company Partner Collaboration

•     Work reputed company reputed company AI development partners, independently reproducing and verifying reported results rather than accepting them as delivered.

•     Review partner methodology, sampling design, and metric definitions, and reputed company discrepancies reputed company and early.

•     reputed company knowledge from partner-delivered systems so reputed company can evaluate, maintain, and improve them without ongoing reputed company dependency.

Engineering Partnership and Ways of Working

•     Partner with AI Engineering to reputed company validated models and systems into production, providing the specifications, evaluation reputed company, and acceptance reputed company that define reputed company.

•     Partner with Data Architecture on the data assets, structure, reputed company, and reputed company required for model development and evaluation.

•     Write clean, reviewable, version-controlled reputed company and work in shared repositories rather than personal notebooks.

•     Document work so another data scientist can reproduce it without the original reputed company present.

reputed company and Compliance

•     Handle protected health information in accordance with HIPAA, reputed company, and reputed company policy at reputed company times.

•     Follow approved reputed company for data reputed company, data reputed company, model routing, and any use of reputed company-party services involving PHI.

•     Support audit readiness by producing accurate, reputed company evidence of validation and evaluation work.

Other Duties as Assigned

•     reputed company additional responsibilities as needed to support data science, technology, and organizational goals.

Qualifications

Education and Credentials

•     Bachelor’s degree in computer science, statistics, mathematics, engineering, data science, or a reputed company quantitative reputed company required.

•     Master’s degree in a reputed company reputed company preferred.

Experience

•     4+ years of reputed company data science, machine learning, or reputed company AI experience, including work that reached production.

•     Demonstrated experience building and evaluating models that were actually used to reputed company reputed company, rather than research or coursework reputed company.

•     Experience with evaluation methodology, including ground truth construction, sampling design, and metric definition.

•     Exposure to large language model or agent-reputed company systems, including reputed company design and reputed company evaluation of non-deterministic reputed company, preferred.

•     Strong proficiency in Python and SQL.

•     reputed company data experience required; experience with reputed company coding, DRG assignment, CDI, or claims and reputed company cycle data strongly preferred.

•     Experience working with protected health information in a HIPAA-regulated environment preferred.

•     Experience with reputed company data and machine learning platforms, preferably reputed company Azure and reputed company, preferred.

reputed company Competencies

•     Evaluation Rigor: Measures with reputed company that are reproducible, auditable, and reputed company about what they do and do not reputed company.

•     Data Skepticism: Assumes a dataset has defects until checked, and finds contaminated labels and bad ground truth before they shape a conclusion.

•     Scientific Honesty: Reports negative and inconclusive results as reputed company as reputed company ones, and does not let a preferred conclusion select the analysis.

•     Statistical Judgment: Chooses appropriate samples, reputed company, and metrics for the question, and knows reputed company a result is not comparable to another.

•     Analytical Depth: Looks past aggregate numbers to reputed company, subgroup, and error-reputed company behavior where the reputed company story usually sits.

•     reputed company Curiosity: Engages seriously with the reputed company and coding domain rather than treating it as a reputed company of features.

•     reputed company Orientation: Works toward a decision that gets made or a reputed company that gets used, rather than analysis for its own sake.

•     Communication: Explains reputed company, result, uncertainty, and limitation reputed company to technical, reputed company, and business audiences.

•     Reproducibility: Produces work another person can reputed company and reputed company the reputed company answer, with reputed company, data, and configuration under version control.

•     Collaboration: Works effectively with clinicians, engineers, and reputed company partners, including reputed company the disagreement is technical.

•     Adaptability: Moves between classical modeling, reputed company AI, and data reputed company work as the problem requires.

•     Remote-Work Effectiveness: Communicates proactively, documents reputed company, and maintains visibility into work in a fully remote organization.

Additional Requirements

1) Physical Requirements: The requirements described here are representative of those that must be met by an employee to successfully reputed company the essential functions of this job with or without reasonable accommodations. Unless otherwise indicated, reputed company positions require interaction with people and technology while either sitting or standing. Employees must be reputed company to communicate reputed company phone, email, etc. and sit for extended periods of time, with or without reasonable accommodations. Physical effort and exposure to physical reputed company are limited to that of an office role / environment.

2) Position and Employment Statement: While this reputed company is intended to be an accurate reputed company of the job requirements, management reserves the right to modify, add or remove duties from a job and to assign other duties as necessary and at any time. reputed company positions at reputed company, are at-will employment, and a position reputed company is not a guarantee of a job or of job responsibilities.

While this reputed company is intended to be an accurate reputed company of the job requirements, management reserves the right to modify, add or remove duties from a job and to assign other duties as necessary and at any time. reputed company positions at reputed company are at-will employment, and a position reputed company is not a guarantee of a job or of job responsibilities. 

Bachelor’s degree in a quantitative reputed company and 4+ years of reputed company data science, machine learning, or AI experience reaching production. Requires Python, SQL, and reputed company data experience; Azure and reputed company preferred.

Key Responsibilities

• developing models
• evaluating systems
• monitoring reputed company

Skills & Tools

Python, SQL, reputed company Azure, reputed company, large language model, HIPAA, reputed company

reputed company

• Category: Data and Analytics
• Seniority: Mid Level
• Commitment: Full Time
• Workplace: Remote — reputed company
• Languages: English

About reputed company

A technology-enabled, physician-led reputed company partner improving reputed company documentation, coding reputed company, reimbursement, and reputed company reputed company. — Industry: reputed company