Senior Ml-Llm Engineer

Job Summary

We are expanding Clinical Intelligence and Workflow Automation capabilities to support clinicians, reduce administrative burden, and improve patient outcomes. We are seeking a Senior Machine Learning / LLM Engineer to design and implement advanced AI systems that enable intelligent decision support, workflow automation, and real-time clinical insights.

This role focuses on building agentic AI systems
, Retrieval‑Augmented Generation (RAG) pipelines, and scalable machine learning infrastructure that integrates with electronic health records, clinical workflows, and operational platforms.

The position collaborates closely with clinicians, product leaders, and engineering teams to deliver safe, reliable, and high‑impact AI solutions in regulated environments.

Other duties and tasks may be assigned as required.

• Design and implement AI agent systems using frameworks such as Lang Graph, Semantic Kernel, or custom orchestration layers
• Build and maintain RAG pipelines grounded in clinical guidelines, evidence‑based medicine, and real‑time patient data
• Develop systems that synthesize fragmented clinical data (EHRs, labs, imaging, clinical notes) into prioritized, actionable insights
• Architect scalable inference services capable of low‑latency performance in clinical environments
• Create evaluation frameworks to ensure AI outputs are accurate, unbiased, and aligned with source‑of‑truth data
• Implement and manage vector search infrastructure using platforms such as Pinecone, Milvus, Weaviate, or equivalent technologies
• Perform model fine‑tuning
  , PEFT/LoRA training, and optimization for production workloads
• Build high‑performance backend services using C# / .NET to integrate AI systems with existing clinical and operational platforms
• Ensure AI systems comply with data privacy, security, and regulatory requirements
• Research emerging AI and ML technologies and apply them to improve clinician productivity and patient care
• Mentor and support engineers on ML, LLM, and AI engineering best practices
• Participate in code reviews and contribute to consistent engineering standards
• Collaborate with cross‑functional teams to translate clinical workflows into automated, intelligent systems
• Maintain regular and reliable attendance

To perform this job successfully, an individual must be able to perform each essential duty satisfactorily.

• Bachelor’s degree preferred
• 5+ years of professional experience in machine learning and LLM engineering, including production‑grade systems

• Deep experience with LLM orchestration
  , tool calling, and long‑context document processing
• Strong proficiency with vector databases (e.g., Pinecone, Milvus, Weaviate)
• Experience with MLOps and deployment pipelines
  , including Docker, Kubernetes, and CI/CD
• Proficiency with C# / .NET for backend and service‑oriented development
• Experience designing scalable, low‑latency inference systems
• Strong understanding of data modeling and workflow mapping
• Familiarity with healthcare interoperability standards such as FHIR and HL7
• Experience with automated testing, unit tests, and AI evaluation frameworks
• Proficiency with version control systems such as Git, TFS, or Azure Dev Ops
• Experience using JIRA or similar task‑tracking tools
• Experience with AI development tools (e.g., Cursor, Copilot)

• Understanding of healthcare data privacy and regulated data environments
• Experience with electronic health records or healthcare claims systems

• Strong analytical and problem‑solving abilities
• Effective written and verbal communication
• Ability to translate complex technical concepts into practical solutions

• Advanced problem‑solving and analytical thinking
• Clear and effective communication
• High standards of confidentiality and professionalism
• Strong interpersonal skills across technical and non‑technical stakeholders
• Ability to multitask efficiently in a professional and calm manner

• Serves as a functional lead on critical initiatives and projects
• Leads consulting or contract resources by assigning tasks and tracking work to ensure timely delivery