opengreenhousegaingels
Senior AI Software Engineer
STOKE Space
LocationKent, Washington; Remote (US), Kent, Remote (US)
WorkplaceFull
Last observed2026-06-13 05:23:09.238028
Job idgaingels-stoke-space-technologies:greenhouse:5807704004
At Stoke, we believe a thriving space economy will enable a vibrant, sustainable, and equitable future here on Earth. That is why we’re building Nova, our fully and rapidly reusable launch vehicle. Designed for daily flight, Nova tackles the core challenges of space transportation by reducing cost, increasing availability, and improving reliability. By radically lowering launch costs and increasing flight cadence, we’re helping create a truly scalable space industry. Our team is mission-driven, collaborative, and empowered to take ownership of their work. If you want to work alongside some of the most dedicated and talented people on Earth, we’d love to have you join us. Description Reusable launch systems are the key to seamlessly connecting Earth and space. An instrumental ingredient to making reusable launch vehicles is the ability to move fast. That is our goal for Boltline by Stoke Space, our commercial software platform that helps advanced hardware manufacturing teams integrate, track, iterate, build, and test efficiently. As a Senior AI Engineer on the Boltline team, you will design, build, and deploy intelligent systems that augment our platform's capabilities—from agentic workflows that automate complex manufacturing processes to RAG pipelines that surface critical institutional knowledge. You'll architect evaluation frameworks to ensure AI reliability, build developer tooling that empowers the team, and integrate LLMs into production systems that accelerate hardware development. The ideal candidate demonstrates deep expertise in applied AI/ML, a high degree of ownership, and curiosity—balancing fast execution with robust, production-grade engineering. Responsibilities Design and implement agentic systems and workflows that automate complex, multi-step manufacturing and engineering processes Build and maintain RAG pipelines leveraging vector databases to enable intelligent search and retrieval Develop comprehensive evaluation frameworks (evals) to measure, monitor, and improve AI system performance, accuracy, and reliability Create developer tooling, SDKs, and internal platforms that accelerate AI adoption across the engineering organization Integrate LLM APIs and orchestration frameworks into production applications Design end-to-end features across the stack using React, TypeScript, GraphQL , and Postgres Lead technical design discussions and contribute to architectural decisions for AI-powered features Partner with pr oduct an d hardware teams to identify high-impact opportunities for AI augmentation Mentor engineers on AI/ML best practices through code reviews, pairing, and design collaboration Participate in Boltline Operational Excellence including participating in on-call r otation and other operational activities Qualifications 4+ years of professional software development experience Hands-on experience building agentic systems, autonomous workflows, or AI-powered automation Experience building RAG architectures, integrating vector databases, and deploying semantic search implementations Experience designing and implementing evaluation frameworks for LLM-based systems Proficiency with full-stack development: TypeScrip t, Rea ct, GraphQL , and relational databases Familiarity with LLM APIs (OpenAI, Anthropic, etc.) and orchestration frameworks Proven ability to own features from concept through deployment and iteration Excellent collaboration and communication skills within cross-functional teams Comfort working in a fast-paced, evolving environment with a focus on delivering impact Preferred Qualifications Degree in computer science or related field/experience Experience with prompt/context engineering and fine-tuning Background in building developer tools, CLIs, or internal platforms Familiarity with Next.js, Apollo (Client/Se rver), H asura, or similar Experience with Docker, Kubernetes/ECS, and AWS infrastructure Familiarity with event-driven architectures using Temporal, Kafka, or similar Hands-on experien
This page is generated from the committed OpenOpps static snapshot. Use the source posting or apply link for the employer's current canonical posting state.