💻 Staff / Principal Software Engineer – AI Platform (LLMs & RAG)
📋 GenAI Healthcare
📍 Hybrid 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 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.
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 RAG, knowledge systems, and AI-native backend architectures.
Responsibilities :
- Design, build, and evolve scalable LLM-based systems, including RAG pipelines, prompt orchestration, embedding strategies, vector search, and inference workflows.
- 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
- Build and maintain backend services and APIs supporting LLM inference, evaluation, observability, and lifecycle management
- Establish best practices for prompt management, model versioning, human-in-the-loop workflows, and continuous improvement using feedback signals.
- 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.
- 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.7+ years of professional software engineering experience, with 2+ years working directly with LLM-based systems in production environments.Hands-on experience designing and deploying RAG architecturesStrong proficiency in Python and experience with modern backend stacksExperience 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 frameworksExperience with cloud-native architectures and containerized deployments📧 Interested in applying? Please click on the ‘Easy Apply’ button