Senior Applied AI Engineer
StackBlitz · Remote
You apply on StackBlitz's own site — MulaJob never submits anything for you without your say-so.
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 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 Senior Engineer on the AI team, you’ll build and improve the core coding AI agents that power Bolt.new. You’ll collaborate directly with product, design, engineering, and data to solve key agent challenges: evaluation harnesses, context compression, maintaining context across large codebases, orchestrating intuitive multi-step workflows, and tackling everything from simple UI tweaks to complex architectural decisions. /p
p This isn't API integration work. You'll be contributing to how AI reasons about and generates full-stack applications, working alongside experienced engineers in a problem space where the patterns are still being invented. Your work ships to millions of users building real products with Bolt.new every day. /p
h4 data-start= 1545 data-end= 1567 🛠️ How You'll Contribute /h4
ul
li strong Build and ship /strong state-of-the-art coding agents for Bolt.new (long-running workflows, context compression, agent loops, model routing). /li
li strong Own /strong agent capabilities end-to-end: planning, tool use, code generation/editing, and maintaining context across large codebases and multi-turn sessions. /li
li strong Integrate and evaluate /strong multiple LLM providers (OpenAI, Anthropic, Google): benchmark quality/cost/latency; choose the right model for each task; and adopt new model features. /li
li strong Design /strong safe, reliable tool-use and workflow orchestration (e.g., Vercel AI SDK, LangGraph): structured actions, guardrails, and production observability. /li
li strong Partner /strong closely with product/design/engineering/data to deliver robust AI features; mentor and raise the bar for peers. /li
li strong Build and maintain /strong evaluation harnesses and datasets; analyze failure modes and user feedback to continuously improve quality and reliability. /li
/ul
h4 data-start= 1663 data-end= 1706 💡 Qualifications /h4
ul
li span class= notion-enable-hover data-token-index= 0 strong LLM Experience: /strong /span Have shipped LLM agents to production environments used by thousands of users. /li
li strong Prompt Engineering: /strong Deep understanding of prompt engineering best practices to guide LLM behavior. Able to craft, refine, and optimize prompts for different tasks and models. /li
li strong Software Engineering Skills: /strong Solid software engineering fundamentals with experience in building production-ready systems. /li
li strong Autonomous Execution /strong : Ability to deliver high-quality work with minimal oversight. Comfortable owning tasks end-to-end, managing complexity, and driving projects to completion within your functional area. /li
li strong Problem-Solving /strong : Strong analytical and problem-solving skills with the ability to debug complex AI behaviors and bring clarity to ambiguous tasks. /li
li strong Data-Driven Mindset /strong : Comfortable collecting, curating, and analyzing data to inform decisions. Able to build datasets, identify patterns in agent behavior, and translate findings into actionable 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 /h4
ul
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
/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 strong data-start= 2144 data-end= 2151 not /strong need to meet every qualification listed above br br /p
/li
/ul