Staff Applied AI Engineer

<h4 data-start="233" data-end="248">🚀 About Us</h4> <p data-start="250" data-end="267">We’re Bolt.new by StackBlitz!</p> <p data-start="269" data-end="558">We’re the team that brought you WebContainers, the first-of-its-kind technology that made it possible to run Node.js right inside your browser. That breakthrough kicked off our journey in 2019, and it’s what powers the blazing-fast online IDE used by over 1 million developers every month.</p> <p data-start="560" data-end="1013">But we didn’t stop there.</p> <p data-start="560" data-end="1013">We doubled down on everything we learned and built&nbsp;<a class="" href="https://bolt.new" target="_new" data-start="637" data-end="669"><strong data-start="638" data-end="650">Bolt.new</strong></a> — the fastest way to go from idea to production without writing traditional code. It’s a next-gen, AI-powered app builder that helps you create, edit, and deploy full-stack web and mobile apps instantly, right in your browser. No installs. No setup. Just smart automation and instant dev environments that let you move at the speed of thought.</p> <p data-start="1015" data-end="1161">We’re a fully remote team, globally distributed, deeply collaborative, and seriously passionate about building the future of software development.</p> <p data-start="1163" data-end="1342">This is your chance to join a small team with a big vision. If you love shipping fast, solving real problems, and pushing the boundaries of what’s possible, we’d love to meet you.</p> <h4 data-start="1349" data-end="1377">✨ About This Opportunity</h4> <p>As a Staff Engineer on the AI team, you'll lead the technical direction of the AI agents that turn natural language into production-ready applications. This means shaping how we work with LLMs to solve our hardest problems: maintaining context across large codebases, orchestrating multi-step workflows that feel intuitive, and handling everything from simple UI tweaks to complex architectural decisions.</p> <p>This isn't API integration work. You'll define the patterns and systems that govern how AI reasons about and generates full-stack applications, driving initiatives across multiple teams and influencing our broader AI strategy. Your work shapes the experience of millions of users building real products with Bolt every day.</p> <h4 data-start="1545" data-end="1567">🛠️ How You'll Contribute&nbsp;</h4> <ul> <li><span class="notion-enable-hover" data-token-index="0"><strong>Define AI Agent Architecture:</strong> </span>Set technical direction for how agents manage context, orchestrate workflows, and scale.</li> <li><strong>Lead multi-model strategy:</strong> Build evals and selection criteria across providers (OpenAI, Anthropic, Google); partner with provider teams to test new capabilities.</li> <li><strong>Build tool-use &amp; workflow foundations:</strong> Design safe, reliable interfaces for tool calling (search, queries, domain actions); evaluate frameworks (e.g., Vercel AI SDK, LangGraph) and set org best practices.</li> <li><strong>Drive cross-team execution:</strong> Align product/design/engineering, resolve tradeoffs, and mentor engineers to raise AI engineering standards.</li> <li><strong>Establish data &amp; evaluation standards: </strong>Own dataset methodology and the eval harness; turn failure modes and conversation insights into measurable improvements.</li> <li><strong>Drive Research and Innovation: </strong>Experiment with prompting, context handling, and post-training; share learnings externally when appropriate.</li> </ul> <h4 data-start="1663" data-end="1706">💡 Qualifications</h4> <ul> <li><strong>Deep LLM experience:</strong> Built and scaled production LLM systems; strong grasp of capabilities, limits, and emergent behavior.</li> <li><strong>Prompt engineering:</strong> Sets best practices and mentors across models and use cases.</li> <li><strong>Software engineering: </strong>Strong fundamentals; designs scalable systems and makes pragmatic architectural calls.</li> <li><strong>Strategic execution:</strong> Drives ambiguous, high-scope work end to end; influences across teams.</li> <li><strong>Systems thinking:</strong> Spots process/communication/technical debt and improves team velocity.</li> <li><strong>Model &amp; agent literacy: </strong>Tracks coding-agent/LLM advances; understands model tradeoffs and the agent lifecycle.</li> <li><strong>Data-driven leadership: </strong>Builds data collection + eval harnesses; turns insights into measurable improvements.</li> <li>Strong verbal and written English communication skills are required, as this role involves frequent collaboration with team members, stakeholders, and customers where English is the primary working language.</li> </ul> <h4 data-start="1850" data-end="1873">🎯 Bonus Points&nbsp;</h4> <ul> <li><strong>Fine-tuning and alignment o</strong>f: LLMs (SFT, RLHF/RLAIF, DPO/ORPO)</li> <li><strong>Machine Learning Background:</strong> Understanding of ML fundamentals and experience with model evaluation metrics.</li> <li><strong>Open Source Contributions:</strong> Experience contributing to or maintaining open-source AI/ML projects.</li> <li><strong>Research Background:</strong> Experience reading and implementing techniques from AI/ML research papers.</li> <li><strong>External Presence:</strong> Experience speaking at conferences, publishing technical content, or representing an organization in industry forums.</li> </ul> <h4 data-start="1974" data-end="1992">📌 A Few Notes</h4> <ul data-start="1994" data-end="2199"> <li data-start="1994" data-end="2043"> <p data-start="1996" data-end="2043">You do <strong data-start="2003" data-end="2010">not</strong> need a college degree to apply</p> </li> <li data-start="2044" data-end="2134"> <p data-start="2046" data-end="2134">You do <strong data-start="2053" data-end="2060">not</strong> need to be located in the U.S. — we’re remote-friendly</p> </li> <li data-start="2044" data-end="2134"> <p data-start="2046" data-end="2134">You do&nbsp;<strong data-start="2144" data-end="2151">not</strong> need to meet every qualification listed above<br><br></p> </li> </ul>