Machine Learning Engineer, Stripe Assistant

Who we are

About Stripe

Stripe is a financial infrastructure platform for businesses. Millions of companies use Stripe to accept payments, grow their revenue, and accelerate new business opportunities. Our mission is to increase the GDP of the internet.

About the team

The Stripe Assistant team is transforming how users interact with Stripe by building an intelligent and proactive assistant that not only answers users' queries but efficiently resolves issues and provides valuable business insights. We leverage LLMs and agentic systems to elevate the user experience across Stripe — from the dashboard to support surfaces — and we enable other teams to build and integrate their AI agents on our platform. We're evolving from a helpful support tool to a trusted pilot that anticipates, optimizes, and executes on behalf of our users.

What you'll do

As a Senior Machine Learning Engineer on the Stripe Assistant team, you'll own the end-to-end ML and agent architecture that makes Stripe Assistant safe, reliable, and deeply useful. You'll set the strategy for how the Assistant executes high-trust actions, delivers accurate analytical answers across Stripe and the broader web, orchestrates capabilities across many tools and agents, and grounds responses in authoritative Stripe and user data.

You'll drive conversation continuity and personalization across surfaces, evolve the Assistant into a proactive partner that anticipates user needs, and deepen its presence in the dashboard to streamline critical workflows. You'll establish rigorous evaluation and SLOs and deliver step-change improvements in quality, latency, cost, and availability — paving the way for configurable levels of autonomy and, ultimately, a dependable operating layer over a merchant's Stripe account.

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 by grounding in authoritative Stripe knowledge and live user data, building cross-surface memory and personalization
• Explore and apply optimal ML methods: fine-tuning LLMs with RLHF, synthetic data generation, optimizing RAG pipelines via domain-specific embedding and retriever fine-tuning, automatic prompt tuning
• Make quality and reliability a product: set and meet SLOs, build rigorous evaluation and benchmarking loops
• Lead as a tech lead: mentor engineers, uphold high bars for code quality, security, observability

Minimum 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
• Proficient in Python (Ruby is a plus); strong distributed systems fundamentals
• Experience working cross-functionally with PM, design, and engineers

Preferred qualifications

• Experience operating ML systems at global scale with stringent SLOs
• Experience building AI/ML-core products, balancing short-term priorities with long-term improvements
• Track record building ML platforms that enable multiple teams to collaborate
• Strong technical leadership and communication