Job description
Our client is a fast-growing fintech startup on a mission to help people make smarter financial decisions through intelligent, AI-native tools. Backed by top-tier investors and led by seasoned entrepreneurs with deep domain expertise, the team is focused on building real-world, high-impact features powered by foundation models.
About the Role
We’re looking for a versatile AI engineer with hands-on experience integrating LLMs into production systems. This is an opportunity to join a small, nimble team where you’ll own core features from concept to launch, helping turn large language models into fast, reliable, and cost-effective user experiences.
Key Responsibilities
Build LLM-powered features such as chatbots, summarization tools, and smart autofill
Select appropriate models (e.g., GPT-4, Claude, open-source) based on accuracy, latency, and cost
Optimize prompts, manage token usage, and apply techniques like Retrieval-Augmented Generation (RAG)
Connect models to real-world data via APIs, databases, and user context
Collaborate across engineering and product to ship experiments quickly and iterate based on user feedback
Stay on top of the latest trends in foundation models, developer tooling, and AI infrastructure
Ideal Candidate
Has shipped LLM features in production and understands the nuances of deploying them at scale
Familiar with OpenAI, Anthropic, Mistral, and similar APIs
Experienced in vector databases and RAG frameworks (e.g., Pinecone, FAISS)
Comfortable writing glue code in Python
Bonus: Hands-on with LangChain, LlamaIndex, or custom AI agents
Thinks in tradeoffs and knows when to use closed vs. open models
Strong product thinking and a bias toward action
Why Join?
Join a mission-driven company solving real problems with AI
Work with a highly experienced founding team and top-tier investors
Competitive compensation and meaningful equity
Comprehensive health, dental, and vision benefits
Remote-first team culture with high ownership and autonomy
