Applied AI Engineer

Russell Tobin; New York (NY); Hybrid; USD 99,187 - 106,075; Full time

Job summary

Russell Tobin is looking for a senior full-stack engineer based in New York, NY for a contract role. This position involves building an enterprise-grade GenAI workflow platform for document data extraction and automated workflows.

The ideal candidate should have over 5 years of full-stack engineering experience with AI/ML platforms, and strong familiarity with GenAI systems. The role offers a hybrid work model with a pay rate of $72 - $77 per hour.

Qualifications

• 2+ years applying GenAI solutions in enterprise environments.
• 5+ years of full-stack engineering experience focused on AI/ML platforms.
• Experience with production-grade GenAI/LLM platforms.

Responsibilities

• Design and enhance GenAI workflows across Lending business lines.
• Build AI-powered document ingestion and data extraction platforms.
• Provide technical leadership on GenAI architecture.

Skills

Experience applying GenAI solutions

Full-stack engineering experience

Building production-grade GenAI platforms

Expertise in LLMOps

Building AI data ingestion pipelines

Advanced retrieval techniques

Understanding evaluation metrics

Managing GenAI systems in production

Tools

Python

Java

Angular or React

Job description

Location: New York, NY (Hybrid 3 Days a Week Onsite)

Duration: 12 Months Contract (Possible Extension)

Payrate: $ 72 - 77 per hour

Job Description

The Fixed Income Technology team is building an enterprise-grade GenAI workflow platform that enables document data extraction, embedded productivity assistants, and automated business workflows across multiple business lines.

This is not a research or proof-of-concept role. We are seeking a senior, hands‑on full‑stack engineer with experience designing, building, and operating GenAI systems in production environments. The ideal candidate understands failure modes, evaluation frameworks, and governance as core components of AI‑powered systems.

Responsibilities

• Design, develop, and enhance reusable GenAI workflows used across Lending business lines.
• Build an enterprise‑grade AI‑powered document ingestion and data extraction platform with traceability, confidence scoring, and human‑in‑the‑loop review capabilities.
• Develop AI‑powered assistants embedded within Lending applications using agentic workflow patterns.
• Deliver automated content generation and presentation/deck creation workflows to support reporting and approval processes.
• Provide technical leadership and guidance on GenAI architecture, including model selection, orchestration patterns, and evaluation strategies.
• Establish and maintain LLMOps practices covering extraction accuracy, assistant reliability, prompt management, and audit monitoring.
• Design and implement controls for entitlements and PII handling when utilizing open‑source models within a regulated environment.
• Serve as a hands‑on technical expert with a clear growth path toward becoming a platform owner responsible for shared GenAI standards across the Lending organization.

Required Skills

• 2+ years of dedicated experience applying GenAI solutions within enterprise business environments, including designing and operating GenAI orchestration frameworks in production beyond vendor‑provided examples (e.g., LangChain‑based systems).
• 5+ years of strong full‑stack engineering experience focused on AI/ML platforms and workflow development using Python or Java.
• Proven experience building and operating production‑grade GenAI/LLM platforms utilizing patterns such as RAG, tool/function calling, agentic workflows, and validated structured outputs.
• Strong expertise in LLMOps, including evaluation harnesses, prompt and version management, regression testing, observability, and reliability measurement for production systems.
• Hands‑on experience building AI‑first data ingestion pipelines with measurable quality, accuracy, and reliability.
• Advanced retrieval expertise, including vector search techniques, multi‑vector and late interaction approaches (e.g., ColBERT, chunking), multi‑stage retrieval pipelines, metadata filtering, and re‑ranking strategies.
• Solid understanding of evaluation metrics and their impact on practical RAG system design, including recall vs. precision, latency vs. quality, MRR, and NDCG.
• Experience managing and operating GenAI systems through real‑world production failures, including model regressions, retrieval degradation, prompt drift, and data quality issues, while designing effective mitigation strategies.

Preferred Skills

• Fixed Income or Institutional Lending domain experience.
• Experience working in regulated environments with strong audit and control requirements.
• Familiarity with enterprise security, data governance, and entitlement models.
• Front‑end development experience using Angular or React.

Accommodations

We are committed to providing reasonable accommodations to applicants and employees with disabilities. If you require a reasonable accommodation to participate in the application or interview process, or to perform the essential functions of this role, please contact us.

Russell Tobin is an equal opportunity employer. We do not discriminate on the basis of the race, religious creed, color, national origin, ancestry, physical disability, mental disability, reproductive health decision making, medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, age, sexual orientation, veteran or military status, or any other characteristic protected by applicable federal, state, or local law.

Russell Tobin is a Fair Chance employer. We consider all qualified applicants, including those with criminal histories, in a manner consistent with applicable state and local Fair Chance laws and ordinances, including, the California Fair Chance Act and all applicable local Fair Chance ordinances.