AI Engineer LLMs & RAG | Fintech Platform Compensation:
$170-200,000k
Location: San Francisco
Who Are We? Were a seed-stage fintech startup on a mission to reinvent private wealth management. Traditionally reserved for ultra-high-net-worth individuals and their armies of advisors, were building a platform that democratizes access to venture capital, private equity, and sophisticated financial services powered by AI. With a live product, paying customers, and strong early traction, were productizing what legacy private banks still do manually. If you're passionate about disrupting dusty institutions with sleek, intelligent systems, we should talk. What's In It for You? Impact from Day One: Help build the foundational AI stack of a startup already generating revenue. Frontline AI Innovation: Work hands-on with GPT-4, Claude, Llama 3, and build RAG and agent architectures from scratch. Fast-Moving Environment: Join a tight-knit team where decisions are made quickly, and your code ships even faster. Ownership: You'll own technical decisions, roadmap contributions, and the full lifecycle of the AI features you build. Momentum + Resources: Were funded by top-tier investors and run lean, which means long runway, high autonomy, and zero bureaucracy. What Will You Do? LLM-First Engineering: Design and deliver features using GPT-4, Claude, and other cutting-edge LLMs. RAG Optimization: Build and tune our RAG pipeline and hybrid search systems for financial data retrieval. AI Agents: Build autonomous agents for investment analysis, portfolio planning, and more. Full-Stack AI Delivery: Own everything from architecture to deployment to documentation. Collaborate Cross-Functionally: Work closely with design, product, and business to translate messy finance into clean user experiences. Stay Ahead: Experiment with and implement the latest in AI (Tree of Thoughts, Constitutional AI, LangGraph, etc.). Team Building: Contribute to growing the AI/ML function as the company scales. What Will You Need? Degree in Computer Science, AI/ML, or related field. 3+ years in software engineering, with 1+ year hands-on with modern LLMs (or 3+ years in AI/ML overall). Strong grasp of: Python, TypeScript LangChain, LangGraph, Pinecone RAG architectures and hybrid search optimization AI agent orchestration using LangChain, AutoGen, or CrewAI Multi-modal data processing (structured data, numerical, and text) Prompt engineering techniques like Chain-of-Thought, Constitutional AI Experience building production-ready AI systems, not just toy projects. High bar for technical communication, documentation, and engineering quality. Startup scars or superpowers ideally you've owned 01 projects in chaotic, ambiguous environments. Willingness to work hard: This team runs 9am9pm, 6 days a week. There's flexibility, but the hustle is real. You're Probably a Fit If You... Get excited by shipping high-impact features, fast. Prefer building in the wild west of early startups vs. optimizing in big orgs. Love both writing code and designing systems. Want to shape the future of AI-powered finance, not just watch from the sidelines. Can handle ambiguity and autonomy like a pro. Are cool with showing up in SF most days or traveling frequently to hang with the crew. Tech Stack Overview: Backend: Node.js / TypeScript (AWS Lambda, Express) Frontend: React Infra: AWS AI Backend: Python, FastAPI, LangChain, LangGraph Vector Store: Pinecone If you've shipped something meaningful with LLMs, have a deep sense of ownership, and want to help reshape financial services from the inside out we're ready when you are.
