Generative AI Engineer

Role:- Applied AI Engineer – GenAI / LLMOps

Location: New York, NY 10019

Duration: Contract – 12 Months

Extension: Possible

Work Arrangement: Onsite/Hybrid – New York, NY

Employment Type: W2 Only | No C2C

About the Role

Our financial services client is seeking a Senior Applied AI Engineer to join the Fixed Income Credit Complex team and help build an enterprise-grade Generative AI workflow platform supporting document intelligence, embedded productivity assistants, and automated business workflows across Institutional Securities.

This is a production engineering role — not a research or prototype position.

We're looking for a senior, hands-on engineer who has successfully designed, built, deployed, and operated GenAI/LLM systems in production. This role offers the opportunity to contribute to a shared enterprise platform and take ownership of core GenAI capabilities, architecture, and engineering standards across Institutional Securities.

What You'll Do

• Design and evolve reusable GenAI workflow primitives and services used across Institutional Securities workflows.
• Build AI-powered assistants embedded into core applications using agentic and tool-driven workflows.
• Define and guide GenAI architecture decisions, including model selection, orchestration patterns, and evaluation strategies.
• Establish and enhance LLMOps practices, including evaluation harnesses, prompt/version management, monitoring, regression testing, and production reliability.
• Design and implement controls for entitlements, data security, and PII handling, including the use of open-source models in regulated environments.
• Develop and maintain AI-first document ingestion and extraction pipelines with measurable quality and accuracy.
• Build sophisticated retrieval systems incorporating vector search, metadata filtering, multi-stage retrieval, re-ranking, and evaluation metrics.
• Diagnose and stabilize production systems affected by model regressions, prompt drift, retrieval degradation, and data quality issues.
• Partner closely with business, engineering, data, and platform teams to drive adoption of shared GenAI capabilities.
• Help establish enterprise standards and best practices for production GenAI engineering.

️ What We're Looking For

• Multi-stage retrieval pipelines
• Vector search
• Re-ranking
• Metadata filtering
• Recall/precision tradeoffs
• MRR
• NDCG
• Strong production debugging skills with experience troubleshooting:
• Model regressions
• Prompt drift
• Retrieval degradation
• Data quality issues
• Production reliability problems
• Strong understanding of software engineering principles, system design, APIs, and scalable production platforms.

⭐ Nice to Have

• Experience within Fixed Income, Credit, Capital Markets, or Institutional Securities.
• Familiarity with enterprise data governance, security models, and entitlement frameworks.
• Experience designing reusable internal platforms, developer tooling, or shared AI capabilities.
• Experience working in highly regulated financial services environments.

Ideal Candidate

The ideal candidate is a hands-on Applied AI / GenAI Engineer who has moved beyond experimentation and has experience taking LLM solutions all the way from architecture and development to production deployment, monitoring, evaluation, and ongoing optimization.

You should be comfortable working across AI engineering, software engineering, retrieval, LLMOps, platform architecture, and enterprise security while partnering with business stakeholders and other engineering teams.

Key Technologies / Keywords

Python | GenAI | LLM | RAG | Agentic AI | LLMOps | Vector Search | Re-Ranking | Embeddings | Tool Calling | Function Calling | Prompt Engineering | Evaluation Frameworks | Observability | AI Agents | Document Intelligence | Document Extraction | Coding Agents | Claude Code | OpenAI Codex | GitHub Copilot | Enterprise AI | AI Platforms