Senior Applied AI Engineer

Requirements

• You’ve shipped LLM-powered features in production
• You know what makes agents fail
• You’re comfortable moving across Type Script and Python
• If that’s you, read on
• 5+ years of industry experience as a Software or Machine Learning Engineer, or a Master’s/PhD in AI, ML, or NLP with 3+ years of production experience
• A track record of shipping LLM-powered features in production—not just API integrations, but real systems with evals, monitoring, and iteration
• Hands-on experience building agentic AI workflows and debugging multi-step agent failures
• Strong command of RAG, context engineering, and retrieval pipeline design
• Experience with transformer models, embeddings, and AI model evaluation
• Proficiency in Python for AI/ML work and comfort working in a Type Script/Node.js codebase
• Familiarity with tools like Hugging Face, Lang Chain, or Mastra
• Excellent communication skills and a collaborative, product-minded approach
• Alignment with our values: a desire to empower others, a focus on team and user success, and a willingness to experiment and learn from failures

• We’re expanding our AI Engineering Team to build next-generation AI‑powered development workflows—enabling users to describe their applications in natural language and have AI generate, modify, and enhance their apps seamlessly
• As an Applied AI Engineer, you will help define and ship the future of AI‑powered development at Bubble
• This is an engineering role, not a research role
• You’ll own LLM‑driven product features end‑to‑end, design agentic workflows that real users depend on, and collaborate closely with Product, Infrastructure, and Research to push the limits of AI‑driven development
• Design and build agentic workflows that enable multi‑step AI‑driven app generation for real users at scale
• Improve LLM reasoning and retrieval techniques to enhance Bubble’s AI‑powered development tools
• Build and maintain production LLM pipelines—including prompt engineering, evaluation frameworks, and latency optimization
• Fine‑tune and optimize LLMs for AI‑assisted app‑building workflows using proprietary Bubble datasets
• Own AI feature quality end‑to‑end: from prototype through eval, deployment, and monitoring
• Work closely with the AI team to scale AI research into production systems