At Spring Health, we’re on a mission to revolutionize mental healthcare by removing every barrier that prevents people from getting the help they need, when they need it.
Requirements
- Proven Experience: Demonstrated experience building and delivering production-grade software, with significant, hands-on experience in LLM or Generative AI engineering.
- A Platform Builder's Mindset: You think in terms of abstractions, reusability, and creating leverage for other engineers. You have experience building internal tools, libraries, or platforms and understand the importance of clear documentation and API design for your internal customers.
- Technical Proficiency: Strong proficiency in Python and familiarity with the modern AI/ML stack, including cloud services (AWS, GCP, or Azure) and CI/CD pipelines.
- LLM & Generative AI Expertise: Hands-on experience building or working with key components of the modern LLM stack. Direct experience with orchestration frameworks (e.g., LangChain, LangGraph), observability tools (e.g., LangSmith), and the infrastructure for Retrieval-Augmented Generation (RAG) like vector databases is a significant plus.
- Pragmatic Problem-Solving: The ability to operate at a feature scope, breaking down clearly defined solutions into smaller, manageable tasks.
- Security and Privacy Awareness: A deep understanding of the importance of handling sensitive data
- Familiarity with cloud services (AWS, GCP, or Azure) and CI/CD pipelines
Responsibilities
- Build Foundational LLM Tooling: Design, build, and maintain the core components of our LLM infrastructure. This includes operationalizing tools like LangSmith for observability, creating shared patterns for using orchestration frameworks, and developing reusable libraries that make our feature teams more productive.
- Develop Advanced AI Capabilities: Build the platform to support sophisticated LLM use cases. You will help deploy and build the pipelines for a vector database to enable Retrieval-Augmented Generation (RAG) across multiple product teams.
- Pioneer Future-State Infrastructure: Contribute to proofs-of-concept and the architectural groundwork for future innovations.
- Ensure Platform Excellence & Scalability: Consistently add logging, monitoring, and alerting to the platform services you build. Your team is accountable to ensure the platform is stable, performant, and cost-effective for its internal users.
- Partner with Feature Teams: Work closely with engineers across the organization to understand their needs and challenges. You will act as a consultant and enabler, providing the tools and patterns that unblock their work and accelerate their AI roadmaps.
- Build the 'paved road' for AI development at Spring Health
- Tackle complex technical challenges by turning clear solutions into well-defined technical plans for LLM Ops and shared LLM components
Other
- Education: A Bachelor's degree in a technical field or equivalent practical experience
- Resilience and Drive: A high degree of grit and comfort with the ambiguity that comes with a fast-paced, high-growth environment
- Ability to work in a hybrid role based in San Francisco, with an expectation to be in office 2-3 days a week
- Ability to earn positive feedback from internal platform users and stakeholders
- Ability to elevate the team by improving internal processes and sharing knowledge through mentorship and documentation
- Ability to work with diverse perspectives and backgrounds
