Senior AI Engineer (Clinical Research)

Job Title: Senior AI Engineer (Clinical Research)

Senior AI Engineer

1. AI/ML Development & Deployment

• Develop and deploy machine learning models for extracting, classifying, and analyzing structured and unstructured clinical data (e.g., EMRs, CRFs, protocols).
• Apply NLP techniques for entity recognition, relationship extraction, summarization, and semantic search of clinical trial texts.
• Build predictive models for trial success, patient recruitment, dropout risk, and adverse event detection.
• Lead the development of GenAI workflows, including LLM/SLM/VLM-based pipelines and multi-modal AI applications.
• Implement computer vision and OCR/IDP models for clinical document processing and imaging.

2. RAG (Retrieval-Augmented Generation) & LLM Engineering

• Design and optimize RAG workflows, including embedding and retrieval pipelines.
• Work with Gemini Flash 2.5 or similar models (e.g., GPT-4, Claude) for LLM-based clinical data tasks.
• Fine-tune prompt engineering, context window optimization, and chunking strategies.
• Integrate and manage vector stores such as FAISS, Chroma, or Vertex AI Matching Engine.

3. Data Engineering & Pipelines

• Collaborate with data engineers to build scalable pipelines for ingesting and transforming clinical and biomedical data (e.g., PubMed, CT.gov, EHR, imaging).
• Handle data cleansing, harmonization, annotation, and transformation for ML readiness.
• Develop ingestion processes for structured and unstructured sources: PDF, SCORM, HTML, internal documents.

4. Evaluation, Monitoring & Regulatory Compliance

• Evaluate models using domain-specific metrics (e.g., precision@k, response confidence) and build continuous feedback loops.
• Ensure transparency, explainability, and reproducibility in model design.
• Maintain compliance with HIPAA, GDPR, and GxP/ISO 13485 standards.

5. Leadership & Collaboration

• Lead and mentor a team of junior data scientists and ML engineers.
• Define and drive AI strategy aligned with clinical and regulatory objectives.
• Collaborate with clinical scientists, statisticians, product managers, and regulatory teams to translate clinical goals into technical AI solutions.

6. Project & Technical Ownership

• Own end-to-end execution of AI projects: scoping, design, development, deployment, monitoring.
• Provide technical direction in deep learning (CNNs, Capsule Networks, Variational Autoencoders, Graph Neural Networks).
• Ensure MLOps best practices, including CI/CD, monitoring, logging, and governance in cloud environments.

Technical Skills & Experience

Must-Have:

• Proficiency in Python (FastAPI/Flask), LangChain, HuggingFace, and vector database integrations.
• Experience with embedding techniques and vector similarity (cosine, dot product, top-k retrieval).
• Hands-on experience with GenAI models (e.g., Gemini Flash 2.5, GPT-4, Claude).
• Knowledge of biomedical ontologies (UMLS, SNOMED CT, MeSH) and EDC systems.
• Familiarity with CDISC, HL7 FHIR, and OMOP CDM standards for clinical data.
• Proven experience in deploying AI models on cloud platforms: AWS SageMaker, GCP Vertex AI, or Azure ML.

Desirable:

• Exposure to MLOps, scientific ML, and data visualization tools.
• Experience with Google Cloud (AlloyDB, Vertex AI APIs, secure deployments).
• Working knowledge of LMS content ingestion (PDFs, SCORM, HTML).
• Familiarity with frameworks like LlamaIndex or Haystack.

Qualifications

• Bachelors or Masters in Computer Science, Biomedical Engineering, Data Science, or related field. PhD preferred.
• 3+ years of AI/ML experience, with 1+ years in clinical research or healthcare.
• Strong leadership, communication, and stakeholder management skills.
• Demonstrated success in translating complex clinical problems into deployable AI solutions.