Senior Applied ML Engineer

ELLKAY, LLC• US,

8d•$170,000 - $210,000•Hybrid

About The Position

Develop applied machine learning and natural language processing capabilities to help ELLKAY understand healthcare data, discover migration scope, extract document content, and retrieve relevant archive evidence. The engineer will work with clinical analysts and DME teams to define labels, train and evaluate models, and preserve clinical meaning. The role owns domain-model quality and experiments from problem definition through production adoption. The engineer will develop schema and document discovery, clinical entity extraction, semantic classification, terminology recommendations, and data-quality anomaly detection. The role combines domain rules, embeddings, supervised models, and large language models while preserving patient context, units, dates, negation, and source references. It also includes prototyping archive search and cited answers, specifying abstention and subject-matter-expert review when evidence is incomplete or clinical meaning is ambiguous, and evaluating pilots for reviewer acceptance, error severity, task time, and performance across source-system families. The role partners with Data Platform and product engineers, clinical and data subject-matter experts, DME/QA, and security teams. It builds reusable services for ELLKAY products while preserving source evidence, approved data-use rights, and tenant isolation. Model or agent proposals follow established human approval and platform release workflows. ELLKAY describes its workplace as hybrid, with flexibility to work remotely for candidates who live more than 40 miles from an office, subject to strong alignment with the role. The position offers a comprehensive benefits package starting on day one.

Requirements

At least 5 years of applied ML, NLP, or equivalent production engineering experience, including model development and evaluation.
Strong Python and SQL skills, applied statistics, experimental design, supervised learning, information retrieval, and NLP using modern ML frameworks.
Hands-on experience with healthcare datasets, EHR/lab workflows, HL7 v2 or FHIR, and clinical terminology.
Experience curating labels, building representative evaluation datasets, analyzing error severity, and preventing leakage across customers or source families.
Ability to combine clinical rules, embeddings, trained models, and LLMs, and measure confidence and abstention.
Ability to work directly with clinical SMEs and communicate model behavior to product and engineering teams.
A relevant degree or equivalent practical experience is acceptable.

Nice To Haves

Knowledge of LOINC, SNOMED CT, ICD-10, or RxNorm.
Experience with OCR/document extraction, clinical negation and temporal reasoning, learning-to-rank, or migration/archive work.
Familiarity with PyTorch, scikit-learn, transformer models, or equivalent tools.

Responsibilities

Develop schema and document discovery, clinical entity extraction, semantic classification, terminology recommendations, and data-quality anomaly detection.
Define clinical relevance labels and benchmarks for mapping source data to ELLKAY's canonical data model and FHIR, archive retrieval, and interoperability recommendations.
Combine domain rules, embeddings, supervised models, and LLMs while preserving patient context, units, dates, negation, and source references.
Prototype archive search and cited answers; specify abstention and SME review for incomplete evidence or ambiguous clinical meaning.
Design pilot experiments and analyze reviewer acceptance, error severity, task time, and performance across source-system families.
Train and adapt models where labeled data and evaluation justify it; compare models against simple baselines and retain source evidence for extracted facts and recommendations.
Partner with Data Platform and product engineers, clinical/data SMEs, DME/QA, and security teams.
Build reusable services for ELLKAY products while preserving source evidence, approved data-use rights, and tenant isolation.
Follow established human approval and platform release workflows for model or agent proposals.