San Francisco, California, United States

Staff AI/ML Software Engineer (genAI / LLM Products)

 Job Description:

Staff AI/ML Software Engineer (GenAI / LLM Products)

We're represeniting our prestigious clinet who is building a next-generation, AI-native platform transforming how people access and experience healthcare. This is an opportunity to join a foundational team shaping intelligent systems that directly impact real users at scale.

We're looking for a product-minded AI/ML engineer who thrives in ambiguity, ships fast, and builds systems that matter.

What You'll Do

  • Design, build, and deploy end-to-end AI-powered products using modern LLMs and orchestration frameworks
  • Own and ship 01 features such as:

    • Conversational AI assistants
    • Intelligent search and retrieval systems
    • Personalized recommendations
  • Develop production-grade RAG pipelines, agent-based workflows, and evaluation systems
  • Build scalable backend systems and APIs powering AI-driven user experiences
  • Work across the stack — from data ingestion and modeling to real-time inference and product integration
  • Partner closely with product, design, and clinical stakeholders to translate complex data into intuitive, high-impact tools
  • Drive technical direction and architecture decisions across AI systems

What We're Looking For

Core Requirements

  • 8+ years of professional experience in software engineering or ML engineering
  • 5+ years building ML systems in production environments
  • Proven experience building and shipping LLM or RAG-based systems in production
  • Strong proficiency in Python and backend development
  • Experience designing and deploying end-to-end ML systems, not just modeling

AI / ML Expertise

  • Hands-on experience with:

    • LLMs (OpenAI, open-source models, etc.)
    • Retrieval-Augmented Generation (RAG)
    • Agent frameworks and orchestration tools
  • Background in:

    • NLP / information retrieval / semantic search
    • Document processing, summarization, or knowledge systems
  • Experience improving system performance through:

    • evaluation frameworks
    • prompt iteration
    • retrieval optimization

Engineering Strength

  • Strong software engineering fundamentals:

    • APIs, distributed systems, and backend architecture
  • Experience building user-facing AI products, not just pipelines
  • Comfortable owning systems end-to-end in production

What Makes You Stand Out

  • You've built AI products used by real users, not just internal tools
  • You've taken systems from idea production iteration
  • You think in terms of user impact, not just model performance
  • You're excited by fast-moving, ambiguous environments and take ownership without waiting for direction
  • Experience in healthcare or regulated environments is a plus, but not required

Not a Fit If

  • Your experience is primarily in:

    • ML infrastructure / platform engineering
    • pure data science or analytics roles
    • research without production deployment
  • You haven't worked with modern LLM-based systems in production

Why This Role

  • Build AI-first products from the ground up, not incremental features
  • Work on problems with real human impact
  • Join a small, high-caliber team where your work directly shapes the product and company trajectory
  • Operate at the intersection of AI innovation and real-world application

Apply now!

  Required Skills:

Data AI Access Modeling Product Design Development Search Pipelines Ownership Healthcare Features Data Science Shipping Architecture Optimization Infrastructure Analytics Integration Research Software Design Engineering Python Science