Principal AI Engineer

Role Description The Principal AI Engineer is primarily responsible for the design, implementation, and support of AI-powered and agentic capabilities embedded in the company’s elluminate software platform. These capabilities facilitate our clients’ work on clinical trials. The Principal AI Engineer will need strong analytical and technical skills to design and build production-grade solutions using Large Language Models (LLMs), agentic frameworks, and modern Deep Learning (DL) and Machine Learning (ML) techniques in close collaboration with the company’s business clients. In addition, the candidate must serve as a Subject Matter Expert on the application of LLMs, agentic AI, and DL/ML to healthcare structured and unstructured data, both internally and with the company’s partners and clients. Your day to day: Actively works with product and engineering to design and build breakthrough AI-powered and agentic capabilities for our clients using LLMs, agentic workflows, and modern DL/ML techniques. Design, prototype, develop, and test LLM-powered applications, agentic workflows, and predictive models using Python and modern AI frameworks to power critical product capabilities. Work with both structured and unstructured clinical trial data, including patient reports, trial documentation, and free text notes. Ideate, design, prototype, and develop solutions such as multi-agent workflows, RAG-based applications, document intelligence and summarization pipelines, and intelligent process automation. Design, prototype, and develop solutions using modern AI frameworks and libraries such as LangChain, LangGraph, LlamaIndex, PyTorch, Hugging Face Transformers, and scikit-learn. Champion AI-driven development practices across the team — using AI coding assistants and agentic dev tools to accelerate prototyping, code generation, testing, and review. Build and maintain LLM, agentic, and ML pipelines, including prompt engineering, orchestration logic, and evaluation harnesses. Apply relevant evaluation frameworks, guardrails, and statistical measures for performance, quality, and error analysis of AI systems. Drive the entire workflow of multiple AI engineering projects. Enhance the experience and efficiency of our elluminate software platform users. Work with our Engineering team to integrate AI capabilities into our elluminate software platform. Work with the MLOps/AIOps team to deploy LLM, agentic, and ML systems in production and to track performance, cost, and quality. Consult with and assist our software development and biometrics teams to consume the results of these AI systems. Ensure data quality throughout all stages of acquisition and processing. Serve as Subject Matter Expert in Generative AI, agentic systems, and applied Machine Learning. Keep up to date with the latest research and tooling in LLMs, agentic AI, and ML. Educate other team members in modern AI techniques and best practices. Publish and present work and contribute to company’s intellectual property. Other duties as assigned. Qualifications Bachelor’s Degree in Computer Science, Engineering, Math, Physics, or a related field; Master’s or Doctorate degree preferred. Accomplished engineer with deep technical credibility and hands-on implementation skills building LLM-powered applications, agentic workflows, and production AI systems; familiarity with modern Deep Learning and Machine Learning techniques (transformers, RAG, fine-tuning, evaluation). Extensive experience shipping production software in a healthcare or life-sciences setting; comfortable working alongside clinicians and domain experts. In-depth knowledge and experience working with healthcare and/or clinical trials data. Expert knowledge of Python and modern AI frameworks (LangChain, LangGraph, LlamaIndex, or equivalents); proficiency with API development, system integration, and at least one major cloud platform (AWS, Azure, or GCP). Pay Range US Pay Ranges: $160,000 - $200,000 USD