Principal Data Scientist

Role overview

Responsibilities

• check_circle Develop LLM-powered automation tools for clinical reporting and document generation workflows
• check_circle Build AI-driven code generation pipelines and quality assessment frameworks
• check_circle Design and implement human-in-the-loop review workflows with feedback loops to continuously improve output quality
• check_circle Design and build multi-agent systems for data workflows — agents that retrieve, generate, validate, and iterate autonomously
• check_circle Implement agent orchestration using frameworks such as Google ADK, LangGraph, or LangChain
• check_circle Deploy and manage agents on Google Vertex AI
• check_circle Use AI coding tools (e.g. Gemini CLI, GitHub Copilot) as a core part of your development workflow
• check_circle Critically review and validate AI-generated code — understanding what it produces, why, and when it’s wrong
• check_circle Write effective prompts to direct AI tools toward correct, secure, well-structured output
• check_circle Know when to use AI and when to write code manually
• check_circle Strong Python skills
• check_circle Hands-on experience building RAG systems or LLM-powered applications (using LangChain, LlamaIndex, or similar frameworks)
• check_circle Experience integrating LLM APIs (Google Gemini, OpenAI, or similar) — we work primarily through Google Vertex AI
• check_circle Working knowledge of vector databases (ChromaDB, Weaviate, Qdrant, Pinecone, or similar)
• check_circle Docker and containerized deployments
• check_circle Comfortable using AI-assisted development tools (e.g. Gemini CLI, GitHub Copilot) — and critically evaluating what they produce

About the company

• check_circle SCRIP – Best Contract Research Organization, Specialist Provider
• check_circle Citeline – 2025 Award Winner
• check_circle Fierce CRO Awards – Recognized Industry Leader