Lead Data & AI Engineer (Clinical EMR)

Team:

Reports to:

Type:

Role Purpose

Build, deploy, and maintain the AI/ML stack powering our EMRclinical NLP/LLM, decision support, and voice scribing. Own end-to-end data engineering, model training, and MLOps with healthcare compliance baked in (PDPA, HIPAA, ISO 27799).

What Youll Do

Data Platform & Pipelines

1. Architect and operate pipelines for structured/unstructured clinical data (EHR notes, HL7 v2, FHIR, audio).
2. Build/maintain the

   feature store

   for clinical AI (labs, meds, allergies, vitals, orders) with lineage & versioning.
3. Implement PHI de-identification/re-identification, KMS-backed encryption, DUAs, and access controls.

Clinical NER & Code Mapping (core accountability)

1. Own the

   extraction + normalization

   stack for: problems/diagnoses, symptoms/findings, medications (

   with attributes

   ), labs, orders, allergies.
2. Ship a

   hybrid extractor

   (transformer NER + rules) with

   assertion

temporality

1. Build a medication attribute parser (dose, unit/UCUM, route, frequency, duration, PRN, instructions).
2. Implement a

   two-stage entity linker

   (candidate gen via lexicon/vector search + cross-encoder rerank) to

   SNOMED CT, RxNorm, LOINC

   ; manage crosswalks to

   ICD-10/CPT

   and local catalogs.
3. Operate

   ontology ops

   : version pinning, diffs, UMLS/SNOMED licensing, regression tests per ontology release.
4. Enforce

   safety guards

   (drugallergy, duplicate therapy, dose range) and confidence-driven UI disambiguation.

Modeling, LLMs & Scribing

1. Build

   RAG/LLM

   pipelines for summarization, CDS, and scribe workflows (prompting, tool use, retrieval, guardrails).
2. Integrate

   ASR + diarization

   with streaming partials/hotwords for clinical terms and names.

MLOps, Reliability & Cost

1. Stand up MLOps: model registry, experiment tracking, CI/CD, canary/shadow deploys, drift & safety monitoring, blue/green rollbacks.
2. Meet SLOs:

   p95 speechdraft less than 2.0s

   , ASR partial updates every

   300500ms

   ,

   99.9%

   uptime, rollback

   less than5 min

   .
3. Optimize inference (Triton/ONNX Runtime, quantization/distillation, caching) and track

   cost per encounter

   .

EHR Integration & APIs

1. Ship SMART on FHIR apps and CDS Hooks; design gRPC/REST services; run Kafka/PubSub with idempotent consumers.

Security, Privacy & Compliance

1. PHI-safe prompts/logs, prompt-injection & data-exfiltration guards, constrained tool allowlists.
2. Audit trails exportable for clinical review & compliance.

Collaboration

1. Partner with Product & Clinical to encode guidelines/rules alongside ML.
2. Mentor engineers; uphold code quality, reviews, and on-call.

Required Qualifications

1. 4+ years Data/ML Engineering (healthcare strongly preferred).
2. Expert:

   Python

   ,

   SQL

   ,

   PyTorch/TensorFlow

   ,

   Hugging Face

   .
3. Deep NLP/LLM (transformers, RAG, prompt engineering, guardrails).
4. Standards:

   FHIR/HL7

   , SNOMED CT, ICD-10,

   RxNorm

   ,

   LOINC

   , CPT; UMLS

familiarity.

1. MLOps (MLflow/Kubeflow/Vertex/SageMaker), containerized inference, CI/CD.
2. Privacy/security in regulated environments (PDPA/HIPAA/ISO 27799).

Nice to Have

1. ASR/diarization (Whisper, Vosk, Kaldi), ONNX/TensorRT, Triton; gRPC/WebRTC streaming.
2. GPU scheduling, vector DBs, OpenTelemetry, Terraform/IaC.