AI/ML Engineer

About Us

We're a startup building a platform focused on finance and generative AI. We work with complex data pipelines, heavy user interfaces, and modern GenAI tools. Our focus is on shipping frequently while maintaining strong product quality and solid architecture. We are heavily investing in our AI capabilities and are looking for a dedicated expert to push the boundaries of our intelligent features.

About the Role

We’re looking for an experienced, highly knowledgeable, and driven AI/ML Engineer to take ownership of our LLM infrastructure and intelligent features. You will be the driving force behind our AI capabilities, responsible for everything from optimizing core LLM interaction speeds (like our intent classifiers) to building complex, personalized agentic workflows.

We need someone who is eager to learn, moves fast, and can own extremely complex problems end-to-end in a fast-paced environment. You will start with high-impact optimizations and quickly move into designing sophisticated features that haven't even been fully conceptualized yet.

What You Will Do

AI Engine Optimization: Drastically improve the performance, speed, and efficiency of our core AI components. You will own and optimize our intent classification pipelines and ensure lightning-fast LLM interactions.

Custom Agentic Workflows: Design, build, and deploy custom, user-specific agentic workflows. You will tie these agents deeply into our skills backend and our frontend agent interfaces to create highly personalized user experiences.

Advanced RAG Systems: Architect and scale our Retrieval-Augmented Generation (RAG) models. You will build the infrastructure to allow our LLMs to seamlessly reference massive datasets, including complex financial research documents, quarterly firm reports, and open-source textbooks with heavy mathematics.

End-to-End Ownership: Take AI features from concept to production, working closely with our full-stack team to ensure robust integration into our core platform.

What We Are Looking For

Experience: Proven track record as an AI/ML Engineer in production environments, with a strong, demonstrable focus on LLMs and generative AI.

AI/LLM Expertise: Deep, hands-on understanding of RAG architectures, prompt engineering, fine-tuning, embedding models, agent frameworks, and LLM optimization techniques.

Backend Proficiency: Strong experience coding in Python. Deep knowledge of FastAPI is a massive plus to integrate smoothly with our backend stack.

Startup Mentality: You have a history of delivering complex features in startups. You are exceptionally eager to learn, capable of moving extremely fast, and comfortable with high autonomy.

Systems Thinking: Ability to design scalable AI pipelines and integrate complex ML models into consumer-facing applications.

Domain Adaptability: Comfortable working with complex data structures, financial documents, and highly technical or mathematical text.