Clinical NLP Data Engineer / Consultant

Job Description

Title: Clinical NLP Data Engineer / Consultant

Company Name: Golden Harvest InfoTech

Vacancy: 01

Age: At least 24 years

Job Location: Dhaka (Mohakhali)

Salary: Negotiable

Experience:

• 3 to 6 years
• The applicants should have experience in the following business area(s): Software Company,Artificial Intelligence (AI) Startup

• Bachelor of Science (BSc)

• 3 to 6 years
• The applicants should have experience in the following business area(s): Software Company,Artificial Intelligence (AI) Startup

• Age At least 24 years

• We`re looking for a highly skilled and dedicated professional with a proven track record in data engineering and clinical NLP. Your profile likely includes: 

• Experience: 3–6 years of hands-on experience in data engineering combined with a strong background in biomedical NLP. You`re familiar with tools like cTAKES, MetaMap, spaCy + medSpaCy, or similar cutting-edge libraries.

• Technical Proficiency: You`re highly proficient in Python and SQL. You also have a solid grasp of at least one workflow orchestrator such as Apache Airflow or Prefect.

• Domain Expertise: A solid grasp of clinical terminology is essential. You`re also comfortable with statistical evaluation metrics (e.g., precision/recall, BLEU score, factuality scores) relevant to NLP and AI model performance.

• Regulatory Acumen: A good understanding of healthcare data privacy regulations (e.g., HIPAA, EU MDR) is crucial for this role.

• As a Clinical NLP Data Engineer / Consultant, you`ll tackle complex challenges at the intersection of healthcare data, NLP, and AI.

• Your core responsibilities will include:Ingesting and normalizing diverse EHR data streams (e.g., HL7, FHIR) and unstructured clinical notes.

• You`ll be adept at mapping this critical clinical data to standard vocabularies like ICD-10, SNOMED CT, LOINC, and RxNorm.Building and optimizing scalable ETL/ELT pipelines using technologies like Apache Spark, Apache Flink, and dbt.

• You`ll also design and manage feature stores that feed our advanced LLM fine-tuning and retrieval-augmented generation (RAG) pipelines.

• Developing sophisticated rule-based and LLM-based concept extractors.

• A critical part of your role will involve red-team testing to identify and mitigate issues such as hallucinations, PHI leakage, and ensure overall clinical safety.

• Curating gold-standard datasets, designing robust evaluation rubrics, and defining prompt guardrails in close partnership with our clinical subject matter experts (SMEs).

• Maintaining meticulous documentation on data lineage, provenance, and data governance artifacts to ensure strict compliance with regulations like HIPAA and EU MDR during compliance audits.

• Collaborating seamlessly with cross-functional teams, including clinicians, data scientists, and compliance officers, to deliver high-impact, compliant solutions.

• Weekly 2 holidays
• Salary Review: Half Yearly
• Lunch Facilities: Partially Subsidize
• Festival Bonus: 2

Weekend: Saturday & Sunday