Senior Applied AI Engineer at StackBlitz

Remote - Remote

Apply
More jobs at StackBlitz

Bolt.new, a product of StackBlitz, is building an AI‑powered app builder that lets developers create, edit, and deploy full‑stack web and mobile apps directly in the browser. The team is fully remote, globally distributed, and focused on shipping fast and thinking big. As a Senior Applied AI Engineer, you will lead the development of AI agents that transform natural language into production‑ready applications, work with cutting‑edge LLMs, design multi‑step workflows, and collaborate across teams to deliver AI‑powered features at scale.

Requirements

Skills

  • Familiarity with TypeScript
  • Hands‑on experience working with Large Language Models (LLMs) and building applications or systems powered by LLMs
  • Deep understanding of prompt engineering best practices to guide LLM behavior
  • Solid software engineering fundamentals with experience in building production‑ready systems
  • Ability to deliver high‑quality work with minimal oversight and own tasks end‑to‑end
  • Strong analytical and problem‑solving skills with the ability to debug complex AI behaviors
  • Comfortable collecting, curating, and analyzing data to inform decisions and translate findings into actionable improvements
  • Strong verbal and written English communication skills

Responsibilities

  • Design and implement AI agent features and extend existing agents with new capabilities, managing context for long conversations or large code bases
  • Leverage models from providers such as OpenAI, Anthropic, and Google, evaluate and choose the best model for a given task, and incorporate new model features
  • Enable the AI agent to call external tools and APIs safely and effectively, implementing structured approaches for web searches, database queries, and domain‑specific operations
  • Collaborate closely with peer engineers and product managers to deliver AI‑powered features that are production‑ready, efficient, maintainable, and well‑monitored
  • Collect and curate datasets from agent responses and multi‑turn conversations, analyze patterns, failure modes, and success signals to derive actionable insights
  • Continuously evaluate AI system performance, experiment with novel techniques, and iterate on prompts, agents, and workflows to improve output quality and reliability

Technologies

TypeScriptOpenAI (GPT series)Anthropic (Claude)Google GeminiVercel AI SDKLangGraphDSPy

Share job

See if your resume is ready for this job

See how our AI can optimize your resume and improve your chances for this role.