Senior Applied AI Engineer

GeneDx (Nasdaq: WGS) delivers personalized and actionable health insights to inform diagnosis, direct treatment, and improve drug discovery. The company is uniquely positioned to accelerate the use of genomic and large-scale clinical information to enable precision medicine as the standard of care. GeneDx is at the forefront of transforming healthcare through its industry-leading exome and genome testing and interpretation services, fueled by the world’s largest, rare disease data sets. For more information, please visit www.genedx.com.

Summary 

As a public and profitable company, we have ambitious plans to scale and enhance our products and services. We're looking for machine learning engineers who can work holistically to design strategic solutions that go beyond just writing code. A strong track record in understanding clinical workflows and business needs, communicating effectively, and delivering impactful results is essential, along with leadership qualities to guide and inspire colleagues. 

As a Senior Applied AI Engineer specializing in Large Language Models for clinical applications, you'll play a key role in advancing ourAI platform and building LLM- powered products that make a meaningful impact in healthcare. You'll have the opportunity to lead large-scale technical efforts developing agentic systems, retrieval-augmented generation (RAG) pipelines, and intelligent clinical assistants that address our long-term business strategies. You'll be expected to propose novel solutions to complex clinical AI challenges, design rigorous evaluation frameworks to measure and communicate model performance to clinical and regulatory stakeholders and optimize LLM systems using modern techniques like DSPy and prompt engineering. The ideal candidate will also have a track record of being an effective thought leader, and improving ML engineering best-practices across the organization. 

Job Responsibilities

• Design, develop, and deploy production-grade LLM systems and agentic workflows for clinical applications, ensuring they are safe, reliable, and clinically validated.
• Lead architecture and system design efforts for complex LLM-based applications including RAG systems, multi-agent frameworks, and clinical decision support tools.
• Develop comprehensive evaluation frameworks and benchmarks to assess LLM performance on clinical tasks, including accuracy, safety, bias, and hallucination detection.
• Implement and optimize prompt engineering strategies using frameworks like DSPy, LangChain, or similar tools to systematically improve model performance.
• Collaborate with clinicians, product managers, regulatory affairs, and engineering teams to translate clinical needs into robust AI solutions that meet healthcare standards.
• Create clear, interpretable metrics and visualizations to communicate model system performance to both technical and non-technical stakeholders, including clinical users and regulatory bodies.
• Mentor and coach ML engineers and data scientists, fostering a culture of responsible AI development, technical excellence, and continuous learning.
• Champion LLM engineering best practices including prompt versioning, evaluation-driven development, safety guardrails, and monitoring for production systems.

Education, Experience, and Skills

• Proficiency in Python, with deep expertise in LLM frameworks and tooling.
• 5+ years experience in ML/AI engineering, with 3+ years specifically working with large language models in production environments. 
• 3+ years experience building and deploying LLM applications using modern frameworks (LangChain, LlamaIndex, DSPy, Haystack, or similar). 
• 3+ years experience with prompt engineering, optimization, and systematic prompt improvement methodologies. 
• 3+ years experience designing evaluation frameworks, benchmarks, and metrics for ML systems, particularly for generative AI and LLMs. 
• 3+ years experience with agentic systems, tool use, function calling, and multi-step reasoning workflows. 
• 3+ years experience with retrieval systems, vector databases, and RAG architectures (e.g., Pinecone, Weaviate, ChromaDB, FAISS). 
• 5+ years experience deploying scalable ML services in the cloud using Docker and Kubernetes (e.g., AWS, GCP, Azure). 
• Strong understanding of LLM safety, including hallucination detection, bias mitigation, and adversarial robustness. 
• Experience with fine-tuning, RLHF, or other model adaptation techniques. 
• Experience with E2E monitoring and observability (e.g., Grafana, Prometheus), user telemetry/alerting, model throughput, and structured logging. 
• Experience building annotation workflows and tooling, ETL/cleaning pipelines, schema design, data provenance tracking, and dataset/version control. 

Bonus points for:  

• Advanced degree (MS/PhD) in Computer Science, Machine Learning, Computational Linguistics, or related field. 
• Prior healthcare / health tech experience, particularly with clinical workflows, EHR systems, or medical documentation. 
• Experience with clinical NLP tasks (medical coding, clinical note generation, diagnosis prediction, etc.). 
• Knowledge of healthcare regulations and standards (HIPAA, FDA guidance on AI/ML medical devices, HL7/FHIR). 
• Publications or contributions in LLM research, clinical AI, or evaluation methodologies. 
• Experience with medical language models (e.g., Med-PaLM, BioGPT, Clinical BERT variants). 
• Familiarity with human-in-the-loop systems and active learning for clinical applications. 
• Experience building guardrails and safety systems for LLMs in high-stakes domains. 
• Experience with CI/CD and MLOps pipelines for ML/LLM systems including automated model deployment, testing, and monitoring. 
• Open-source contributions to public GitHub repositories related to LLMs, RAG, or clinical AI. 
• Prior experience integrating LLM systems into EHR workflows (SMART on FHIR apps, CDS Hooks, or other FHIR-based integrations). 

Acknowledgements

The above job description is not intended to be an all-inclusive list of duties and standards of the position. Incumbents will follow any other instructions, and perform any other related duties, as assigned by their supervisor.