Machine Learning Engineer, Stripe Assistant

Stripe is a financial infrastructure platform for businesses, aiming to increase the GDP of the internet by providing payment solutions and business growth tools. The company is seeking to enhance its AI-driven Assistant to improve user interactions, issue resolution, and business insights.

Location: United States

Responsibilities

• Establish trustworthy, human-in-the-loop execution for high-trust “write” actions—prioritizing user control, transparency, accountability, and auditability.
• Define and evolve the Assistant’s capability and governance model across hundreds of tools and agents.
• Raise answer quality and usefulness by grounding in authoritative Stripe knowledge and live user data, building cross-surface memory and personalization.
• Explore and apply optimal machine learning methods to improve Stripe Assistant’s overall performance, including fine-tuning LLMs with RLHF, synthetic data generation, optimizing RAG pipelines via domain‑specific embedding and retriever fine‑tuning, and automatic prompt tuning.
• Make quality and reliability a product: set and meet SLOs, build rigorous evaluation and benchmarking loops, and drive sustained improvements in latency, cost, and availability.
• Lead as a tech lead: mentor and grow engineers, uphold high bars for code quality, security, observability, and operational rigor, and align cross‑functionally to ship safely and fast.

Requirements

• 5+ years in AI/ML and backend engineering.
• Applied LLM experience: RAG/embeddings, tool use/function calling, agentic planning/orchestration, fine-tuning, code generation, evaluations, etc.
• Proficient in Python (Ruby is a plus); strong distributed systems fundamentals.
• Experience working closely with product management, design, other engineers, and other cross-functional partners.