Job Description
💻 Staff / Principal Software Engineer – AI Platform (LLMs & RAG)
📋 GenAI Healthcare
📍 Hybird in SF
💸 Competitive base + hefty bonus
We are working with a pioneering generative AI-native health company revolutionizing hyper-personalized care. Its precision care platform empowers physicians with AI-driven copilots, enabling a new era of whole-person care through generative and predictive intelligence. They tap into cutting-edge resources, have an extensive dataset covering 100s million patients and a network of 1.8 million healthcare professionals across 300,000 facilities. The company brings together top healthcare and technology experts, operators, and leading clinical advisors to drive innovation in precision medicine.
We are seeking a Staff / Principal Software Engineer to provide technical leadership in building, scaling, and operating LLM-powered healthcare applications, with a strong emphasis on Retrieval-Augmented Generation (RAG), knowledge systems, and AI-native backend architectures.
This role is ideal for a senior technical leader who has designed and productionized LLM systems, worked with clinical, healthcare, or healthtech data, and can operate at both architectural and implementation depth. You will play a critical role in shaping the AI platform that powers clinician-facing copilots and decision-support tools, while ensuring correctness, safety, scalability, and regulatory compliance.
Responsibilities:
LLM & RAG System Architecture
- Design, build, and evolve scalable LLM-based systems, including RAG pipelines, prompt orchestration, embedding strategies, vector search, and inference workflows.
- Architect knowledge retrieval systems that combine structured and unstructured clinical data (guidelines, policies, patient context, claims, formularies, etc.).
Healthcare & Clinical AI Applications
- Develop AI services that operate on healthcare and clinical data while respecting FHIR, HL7, HIPAA, and other regulatory and compliance requirements.
- Partner closely with clinical, product, and data science teams to translate real-world clinical workflows into reliable AI-driven experiences.
AI Platform & Backend Engineering
- Build and maintain backend services and APIs supporting LLM inference, evaluation, observability, and lifecycle management.
- Implement fault-tolerant, secure, and high-availability systems capable of operating at healthcare scale.
Evaluation, Safety & Quality
- Lead the design of LLM evaluation frameworks (hallucination detection, grounding, faithfulness, latency, cost, and clinical relevance).
- Establish best practices for prompt management, model versioning, human-in-the-loop workflows, and continuous improvement using feedback signals.
Technical Leadership & Mentorship
- Act as a technical authority across teams, influencing architecture decisions and long-term platform strategy.
- Mentor senior and mid-level engineers, set engineering standards, and raise the bar on system design and code quality.
Cross-Functional Collaboration
- Work closely with data engineering, data science, security, and product leadership to align AI capabilities with business and clinical objectives.
Minimum Qualifications:
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
- 10+ years of professional software engineering experience, with 3+ years working directly with LLM-based systems in production environments.
- Hands-on experience designing and deploying RAG architectures, including embeddings, vector databases, retrieval strategies, and prompt orchestration.
- Strong proficiency in Python and experience with modern backend stacks (REST/gRPC APIs, async systems, microservices).
- Experience working in healthtech, healthcare, life sciences, or clinical data environments, including exposure to regulated data.
- Proven ability to design systems that are scalable, secure, observable, and maintainable.
Preferred Qualifications:
- Experience integrating LLMs with EHR data, clinical guidelines, prior authorization rules, quality measures, or real-world evidence datasets.
- Familiarity with LLM evaluation tooling and frameworks (e.g., RAGAS, custom eval pipelines, automated and human feedback loops).
- Experience with cloud-native architectures (preferably Azure) and containerized deployments.
- Knowledge of data privacy, governance, and security best practices in healthcare environments.
- Experience influencing technical direction at Staff or Principal scope across multiple teams or systems.
Benefits:
- Competitive salary and performance-based bonuses.
- Opportunities for professional growth and leadership in a rapidly scaling AI-native healthcare company.
- Collaborative, mission-driven work environment with top-tier clinical and technical talent.
- Opportunity to build cutting-edge AI systems with real-world clinical impact.
📧 Interested in applying? Please click on the ‘Easy Apply’ button