Software Engineer - AI Applications

Eleven Recruiting; New York (NY); On-site; USD 140,000 - 210,000; Full time

Job summary

Eleven Recruiting represents a client investment firm hiring a Software Engineer, AI Applications in New York, NY. You will integrate LLM-powered features and design data layers to make AI outputs explainable and auditable.

The role emphasizes building backend services, defining patterns for AI capabilities, and delivering near-term agentic workflows such as meeting briefs and summaries. A strong emphasis on production-grade shipping and collaboration across teams is required.

Qualifications

• 5–8 years of software engineering experience with a backend or fullstack foundation.
• 2+ years building and shipping LLM-powered applications to production.
• Experience integrating AI capabilities via APIs, data pipelines and product codebases.
• Hands-on experience with RAG pipelines, prompt engineering at scale, and LLM evaluation.

Responsibilities

• Integrate LLM-powered features into an existing product within codebases and UI patterns.
• Design a data and metadata layer for explainable, auditable AI outputs.
• Set engineering patterns for building, testing, evaluating, and maintaining AI capabilities.
• Scope and ship near-term, high-ROI agentic workflows (e.g., meeting prep briefs, summaries).
• Build backend services and APIs that synthesize internal data into client outputs.
• Take on additional projects as needs evolve.

Skills

Backend development

Fullstack foundations

LLM integration

APIs and data pipelines

RAG pipelines

Prompt engineering

Production-grade shipping

Tools

LangGraph

CrewAI

Job description

We are a specialized technology staffing agency supporting professional and financial services companies. Why do we stand out in technology staffing? We listen and act as advisors for our candidates on how they can best add value, find interesting projects, and pave a path for career advancement. We advocate for best pay, diversity in tech, and best job-fit for every candidate we place.

Our client, an investment firm, is seeking a Software Engineer, AI Applications to join their team in New York, NY!

Responsibilities

• Integrate LLM-powered features — including search, summarization, and workflow automation — into an existing product, working within established codebases and UI patterns.
• Design a data and metadata layer that makes AI outputs explainable, auditable, and reusable across teams.
• Set engineering patterns for how AI capabilities are built, tested, evaluated, and maintained going forward.
• Scope and ship near-term, high-ROI agentic workflows — such as automated meeting prep briefs, pipeline summaries, and relationship intelligence digests.
• Build backend services and APIs that synthesize internal data, activity history, and context into client-ready outputs.
• Take on additional projects and responsibilities as needs evolve across the engagement.

Qualifications

• 5–8 years of software engineering experience with a strong backend or fullstack foundation.
• 2+ years of focused experience building and shipping LLM-powered applications to production — not just prototypes.
• Solid understanding of how to integrate AI capabilities into existing systems: APIs, data pipelines, and product codebases.
• Hands-on experience with RAG pipelines, prompt engineering at scale, and LLM evaluation.
• Pragmatic product sensibility — able to identify what is worth building, scope it tightly, and ship it.

Preferred

• Experience with agent orchestration frameworks such as LangGraph or CrewAI.
• Domain exposure in financial services — credit, capital markets, deal workflow, or client coverage.
• Experience building in regulated environments where auditability and explainability are required.
• Familiarity with CRM data models or client intelligence tooling.

What This Role Is Not

This is not a machine learning research role, and we're not looking for someone whose primary background is model training or data science. The ideal candidate thinks of themselves as a software engineer first — one who has developed deep expertise in applying LLMs to real product problems.