Research Data Technician
VCU School of Public Health is seeking a Research Data Technician to join their Department of Biostatistics. The role involves building an LLM based information retrieval engine, developing secure APIs, and ensuring compliance with data privacy standards.
Responsibilities
- Build RAG Pipelines: Design and implement robust data pipelines to ingest, clean, chunk, and embed unstructured text data (PDFs, HTML, text) into a Vector Database
- Develop Secure APIs: Build the backend infrastructure using Python (FastAPI or Flask) to serve AI inferences to internal web applications
- Orchestrate LLM Logic: Use frameworks like LangChain or LlamaIndex to manage the interaction between user queries, the knowledge base, and the LLM
- Optimize for Accuracy: Implement 'Grounding' techniques to ensure model outputs are accurate, factual, and cited—critical requirements in a medical setting
- Privacy & Compliance: Collaborate with our IT security team to ensure all AI deployments adhere to strict HIPAA and data privacy standards
Skills
- Strong Proficiency in Python: comfortable writing production-ready code, not just notebook scripts. Experience with Pandas/NumPy is required
- Generative AI Experience: You understand the RAG architecture. You have likely built a project using OpenAI APIs, Hugging Face, or local LLMs (Llama 3, Mistral)
- API Development: Experience building RESTful APIs to connect data science models to front-end interfaces
- Demonstrated experience and flexibility working in and fostering an environment of respect, professionalism, and civility with a population of faculty, staff, and students from various backgrounds and experiences, or a commitment to do so as a staff member of VCU
- Currently enrolled in or recently graduated from a Master's or PhD program in Computer Science, Data Science, Bioinformatics, or a related field
- Hands-on experience with Vector Databases (ChromaDB, Pinecone, Milvus, etc.)
- Familiarity with containerization (Docker) for deploying applications
- Interest in NLP (Natural Language Processing) specifically within the healthcare or biomedical domain
Benefits
- All VCU employee types are eligible for a wide array of benefits to support you during your employment at VCU. Consult the benefits website for information on benefits eligibility according to employee type.
Company Overview
Company H1B Sponsorship