Staff Software Engineer, AI Tooling

At Vast, our mission is to contribute to a future where billions of people are living and thriving in space. Vast is developing next-generation space stations to ensure a continuous human presence in space for America and its allies, enabling advanced microgravity research and manufacturing, and unlocking a new space economy for government, corporate, and private customers. Using an incremental, hardware-rich and low-cost approach, Vast is rapidly developing its multi-module Haven Station. Haven Demo’s 2025 success made Vast the only operational commercial space station company to fly and operate its own spacecraft. Next, Haven-1 is expected to become the world’s first commercial space station when it launches, followed by additional Haven modules to enable permanent human presence by 2030. Our team is all-in, committed to executing our mission safely and on time. If you want to work with the most talented people on Earth furthering space exploration for humanity, come join us. Vast is looking for a Staff Software Engineer, AI Tooling reporting to the Senior Manager, Software Engineering to support the development of the systems that will be required for the design and build of artificial-gravity human-rated space stations. This will be a full-time , exempt position located in our Long Beach location. Responsibilities: Define the technical direction and long-term roadmap for Vast's internal AI platforms and tooling Architect and lead the development of full-stack AI applications that serve diverse use-cases across the company Establish engineering best practices, design patterns, and quality standards for AI systems development Build and maintain production-grade integrations connecting AI models with internal tools, data sources, and workflows Design and implement pipelines for AI response enforcement, content safety, and output formatting Drive the evaluation and adoption of emerging AI frameworks, models, and patterns to continuously improve internal tooling Collaborate cross-functionally with IT Infrastructure, security, and business stakeholders to integrate AI tooling with existing systems Mentor and guide other engineers contributing to AI initiatives, fostering a culture of technical excellence Ensure the reliability, observability, and scalability of production AI systems Rapidly iterate on AI tooling as the technology landscape and company needs evolve Minimum Qualifications: Bachelor's degree in computer science, math, an engineering discipline, or equivalent work experience 8+ years of software development or relevant industry experience Proven track record of leading technical initiatives from concept through production deployment Strong full-stack development proficiency with experience across both frontend and backend systems Deep understanding of AI/ML concepts, large language model architectures, prompt engineering, and modern AI tooling patterns Demonstrated experience implementing and maintaining production applications at scale Experience establishing engineering best practices and providing technical mentorship Strong cross-functional communication skills with the ability to translate technical concepts for diverse audiences Preferred Skills & Experience: Experience with Python and TypeScript in production environments Experience with Svelte or SvelteKit Experience with OpenWebUI or similar open-source AI interface platforms Experience building or integrating MCP (Model Context Protocol) servers and gateways Experience with LLM API integration and AI pipeline development Experience with containerization and deployment (Docker, Kubernetes) Familiarity with RAG (Retrieval-Augmented Generation) patterns and vector databases Experience building or leading AI/ML platforms at scale Prior experience as a tech lead or in a similar engineering leadership role Experience working in fast-paced, ambiguous environments with evolving requirements Additional Requirements: Ability to travel up to 10% of the time Willingn…