Applied AI Engineer

About Slash

Started in 2021, Slash is one of the fastest growing fintechs in the world and we power over ten billion dollars a year in business purchasing across numerous industries. We recently raised a $100M Series C led by Ribbit Capital with participation from Khosla Ventures, Goodwater Capital, NEA, and Y Combinator, accelerating our expansion into new markets and products.

Slash is headquartered in San Francisco, and has a strong in-person culture.

About the role

Slash is building an AI-native financial platform, and we're forming Slash AI Labs, a small, high-leverage team responsible for bringing AI deeply into every surface of the product. We've already shipped Twin, our agent platform powered by a custom orchestration runtime, tool-calling over a structured ontology graph, MCP, and multi-surface delivery across web, Slack, and API. You'll be an early member of this team and helping incubate what comes next. If you want to build production AI systems at a fintech that's growing fast and ships constantly, this is the role.

What you’ll do

• Ship full-stack AI features end to end, from prompt engineering and agent orchestration to React UI and API integration
• Build and extend our agent runtime: orchestration, tool execution, MCP servers, graph-based conversation state, and context compaction
• Design and implement multi-surface agent experiences across web, Slack, and programmatic APIs
• Build internal AI tooling and platforms, model evaluation frameworks, prompt management, and LLM observability tooling
• Work directly with Anthropic and OpenAI APIs, the Vercel AI SDK, and our custom orchestration layer to solve challenging problems in tool-calling, long-context management, and multi-step reasoning
• Improve and scale our AI infrastructure: inference routing, model tiering, prompt caching, and streaming architecture on AWS/EKS

We’re looking for someone who

• Has shipped full-stack AI products to production, not just prototypes, but systems that serve real users reliably
• Is proficient in TypeScript or modern web frameworks (React, Next.js, Node.js) with strong backend fundamentals
• Has hands-on experience with LLM APIs (Anthropic, OpenAI), with a strong grasp on tool-calling, structured output, and streaming
• Can build and iterate quickly, you're a builder who ships, not someone who over-plans
• Has experience with one or more of: agent orchestration, MCP, RAG, structured extraction, or model evaluation