Senior AI Engineer

Dover, Delaware

Software Engineering

Permanent

Our client is a venture-backed fintech startup, is hiring a Senior AI Engineer to join the team full-time in New York. The successful candidate will take end-to-end ownership of the company’s AI capabilities, from models and data pipelines to evaluation, observability and production standards, while also helping shape the future direction of its AI function and team.

Responsibilities

Design, build and deploy LLM-powered systems that extract structured data from complex documents across multiple formats.
Develop detailed source citation, confidence-scoring and human-in-the-loop review capabilities to ensure outputs are accurate and traceable.
Build entity-resolution systems that reconcile information from banks, credit bureaus, government agencies, courts and family-provided records.
Convert structured estate data into accurate, court-ready documents and filings.
Create robust evaluation frameworks, ground-truth datasets, and automated regression tests for production AI systems.
Implement monitoring and observability tools to track model quality, reliability, latency and cost.
Develop intelligent routing strategies across multiple model providers, balancing accuracy, performance and cost.
Own the underlying AI infrastructure, including data pipelines, retrieval systems, vector databases and deployment workflows.
Establish the technical, evaluation and quality standards used to determine when AI capabilities are ready for production.
Help build and scale the company’s AI engineering function, shaping its technical direction, processes and future team.

Skillset

Proven experience designing, building and deploying production-grade LLM or machine learning systems used by real customers.
Hands-on experience with document intelligence, information extraction, RAG, AI agents or similar AI applications.
Experience developing technology in high-stakes environments where accuracy, traceability, compliance and reliability are essential.
Strong understanding of model evaluation, including how to measure performance, validate outputs and make AI-generated decisions explainable and defensible.
Advanced proficiency in Python.
Practical experience building and maintaining production data and AI pipelines.
Strong knowledge of vector databases, retrieval architectures, model evaluation techniques and routing across multiple LLM providers.
Ability to independently own the supporting AI infrastructure without relying on a dedicated platform team.
Experience as a founding or early-stage engineer, technical founder, first AI/ML hire, or someone who has established an AI function within a growing company is highly valued.