We are hiring an Applied AI Engineer to join a Fixed Income Institutional Lending Technology team building an enterprise-grade GenAI workflow platform. This is a 12-month contract position based in New York City. This is a hands-on technical role—not research or demo work—focused on designing, building, and operating production GenAI systems with rigorous attention to failure modes, evaluation, and governance. You will work toward becoming a platform owner responsible for shared GenAI standards across the Lending business.
Responsibilities
Design and evolve reusable GenAI workflows used across Lending business lines.
Build an enterprise-grade AI document ingestion and data extraction capability, including traceability, confidence scoring, and human-in-the-loop review.
Develop AI-powered assistants embedded in Lending systems using agentic workflows.
Deliver automated content and deck generation workflows for reporting and approvals.
Advise on GenAI architecture: model selection, orchestration patterns, and evaluation strategy.
Establish LLMOps practices covering extraction accuracy, assistant reliability, prompt management, and audit monitoring.
Design and implement controls for entitlements and PII handling, including safe use of open-source models in a regulated environment.
Qualifications
Required
5+ years of front-to-back engineering experience in Python or Java, with a focus on AI/ML platforms and workflows.
Show the full description
2+ years of dedicated, practical GenAI experience in an enterprise business environment, including designing and operating orchestration frameworks in production beyond vendor examples (e.g., custom LangChain-based systems).
Proven experience building and operating production-grade GenAI/LLM platforms applying RAG, tool/function calling, agentic workflows, and validated structured outputs.
Strong LLMOps expertise: evaluation harnesses, prompt and version management, regression testing, observability, and reliability measurement in production.
Hands-on experience building AI-first data ingestion pipelines with measurable quality, accuracy, and reliability.
Advanced retrieval depth: multi-vector and late-interaction approaches (e.g., ColBERT), chunking strategy, multi-stage retrieval pipelines, metadata filtering, and re-ranking—plus working command of evaluation metrics (recall vs. precision, latency vs. quality, MRR, NDCG) and how they shape RAG design.
Experience operating GenAI systems through real production failures—model regressions, retrieval degradation, prompt drift, data quality issues—and designing mitigations.
Preferred
Fixed Income or Institutional Lending domain experience.
Experience in regulated environments with strong audit and control requirements.
Familiarity with enterprise security, data governance, and entitlement models.
Experience building reusable internal platforms or shared developer tooling.
Frontend experience (Angular or React).