Generative AI Engineer Finance Platform; NYC On-Site

The OTC derivatives market moves trillions of dollars daily on infrastructure that hasn't fundamentally changed in decades. We're building the platform for the next evolution of financial services.

We're a small team that came from trading, quant, and engineering roles at tier one financial institutions who were previously responsible for creating some of the most innovative products in the market. We are now building a platform which can process the most complex transactions executed across financial markets. We are building this right: delightful experience, modern stack, AI-native architecture.

Our clients are the most sophisticated banks, hedge-funds, and asset managers in the world. The problems are extremely hard, the scale is massive, and we're creating infrastructure that will define how this market operates for decades to come.

You'll build the generative AI systems behind a modern OTC derivatives platform. These are agents and AI workflows that work alongside traders, operations teams and risk managers. They read complex financial documents, reason over derivative data and take action inside real workflows.

• Build AI agents and workflows that automate work across the OTC landscape, from interpreting unstructured inputs to coordinating multi-step tasks across our platform.
• Own evaluation and context engineering. Build the eval frameworks, datasets and tracing that keep model outputs high-quality, reliable and explainable in a domain where accuracy matters.
• Design retrieval, grounding and validation pipelines for complex derivative data. You'll work closely with financial engineers and domain experts to encode deep market knowledge into our AI systems.
• Turn documents into structured knowledge by building tools that extract, validate and reconcile information from trade documents and keep data consistent across systems.
• Bring AI reasoning into critical workflows such as trade booking, settlement, valuation and risk management, with humans approving the decisions that matter.
• Ship to production with real users, iterate quickly and see your impact right away.

This role is for someone who wants to work at the cutting edge of applied LLMs and agents on hard, high-stakes problems, where reliability, auditability and domain depth matter as much as model capability.

• Bachelor's degree in Computer Science, Engineering, Mathematics, Financial Engineering or a related field
• This role is based in person at our NYC office
• Strong proficiency in Python; knowledge of Typescript/React is a plus
• Hands-on experience building LLM-powered agents, including tool calling, multi-step reasoning, orchestration and agent harnesses
• Experience designing and running evals, such as building datasets, LLM-as-judge and custom evaluators, and regression testing for model and prompt changes
• Strong context engineering skills: retrieval and grounding strategies, and managing context for long-running agents, prompt design.
• Ability to pick up domain knowledge quickly for all parts of the agent development life cycle
• Proficiency in structured output generation and extraction
• Experience with LLM observability and tracing tools (e.g., Lang Smith, Logfire) for debugging and improving model behavior in production
• Familiarity with cloud infrastructure and deployment tools (CDK, Terraform) and cloud providers (e.g., AWS, GCP, Azure)
• Strong understanding of traditional and AI SDLC and software design principles
• Up to date with AI ecosystem and trends
• Excellent problem-solving and communication skills

• Experience with agent frameworks such as Lang Graph
• Knowledge of OTC derivatives, trade lifecycle ISDA, Financial Data (market and reference data)
• Experience fine-tuning models or applying reinforcement learning to LLMs