Description

You will design, build, and operate production-grade GenAI platforms and workflows for institutional lending systems.

This role is on-site.

Responsibilities

• Design and evolve reusable GenAI orchestration frameworks (LangChain) for document data extraction, embedded assistants, and automated reporting.
• Build AI-first data ingestion pipelines with traceability, confidence scoring, and human-in-the-loop review capabilities.
• Implement LLMOps practices including evaluation harnesses, prompt version management, regression testing, and observability in production.
• Establish controls for entitlements, PII handling, and audit monitoring within regulated environments.
• Provide expert guidance on model selection, retrieval strategies, and governance for AI-powered systems.

Required Skills

• 5+ years of full-stack engineering experience with Python or Java.
• 2+ years dedicated experience applying GenAI solutions in enterprise business environments.
• Proven track record building production-grade GenAI/LLM platforms using RAG, tool/function calling, and agentic workflows.
• Strong LLMOps expertise: evaluation metrics (MRR, NDCG), prompt management, and reliability measurement.
• Advanced retrieval experience with vector search, multi-stage pipelines, metadata filtering, and reranking (e.g., ColBERT).
• Frontend experience with Angular or React is a major plus.
• Experience operating systems through production failures including model regressions and prompt drift.

Preferred Skills

• Fixed Income or Institutional Lending domain experience.
• Familiarity with enterprise security, data governance, and entitlement models in regulated environments.

Key Skills

Education

Any Graduate