Role
Extend the Python processing pipeline that enriches EMS patient care records before they reach search and dashboards.
Work under the client’s technical lead on a backlog defined sprint by sprint.
Responsibilities
- Build new enrichments (syndromes, performance measures and similar derived fields) in the existing framework, to given definitions, with tests.
- Help build probabilistic linking of multiple EMS records to one incident and one patient, using time, location and record attributes; harden the existing patient-token logic.
- Work within the existing Python processors, message-queue pipeline and MongoDB record store; keep new processing consistent with how records are versioned and re-processed.
- Validate results on obfuscated data in staging; trace and explain differences against the current path.
Required skills
- Python, 4+ years, building data processing in an existing codebase.
- Applied data science: entity resolution / probabilistic matching, classification from text, feature derivation from structured records.
- MongoDB working knowledge; understanding of how a search index (Solr or similar) consumes processed records.
- Linux AWS familiarity sufficient to run and debug a pipeline.
- Comfortable taking technical direction from a client lead and working from a lightly defined backlog.
Preferred
- EMS, healthcare or public-health data (NEMSIS, ICD, RxNorm, syndromic surveillance).
- NLP on clinical or incident narratives; geospatial data and geocoding.
- Exposure to Azure Data Lake, Databricks or Fabric.
Rate:
Not specified
Location:
Remote
IR35 Status:
Not specified
Remote Status:
Remote
Industry:
Data & Analytics
Seniority Level:
Mid-Level