AI Expert/Architect

New York Technology Partners; United States; On-site; USD 180,000 - 240,000; Full time

Job summary

New York Technology Partners seeks an experienced Architect to design and build enterprise-grade Generative AI applications. You will orchestrate LLMs, retrieval, and structured data into robust, scalable workflows.

You will lead multi-step reasoning systems with LangGraph/LangChain, ensuring state management, tool calls, and human-in-the-loop controls. Strong mentoring and production-quality code are essential for safe, observable AI delivery.

Qualifications

• 15+ years of experience building large-scale distributed systems, platforms, or enterprise applications.
• Proven track record shipping production AI/LLM-powered applications — agentic workflows, RAG systems, or intelligent automation.
• Deep expertise in Generative AI: LLMs (OpenAI), Prompt Engineering, RAG, vector search, and AI agent orchestration.
• Hands-on experience with agent frameworks: LangChain, LangGraph, AutoGen, or equivalent.
• Frontend and backend background to integrate AI solutions end-to-end into existing applications.
• Strong software engineering fundamentals: system design, algorithms, testing, debugging, and code review.
• Demonstrated ability to lead technical direction and mentor engineers.
• Comfort in ambiguous, fast-moving problem spaces where best practices are still emerging.
• BS, MS, or PhD in Computer Science, Engineering, or equivalent practical experience.

Responsibilities

• Architect and build enterprise-grade Generative AI applications combining LLMs, retrieval, structured data, orchestration, and workflow automation.
• Design agentic systems and multi-step reasoning workflows using LangGraph or equivalent — with clear control over state, memory, tool invocation, and human-in-the-loop checkpoints.
• Build fault-tolerant orchestration for long-running AI workflows using Temporal or similar platforms.
• Drive reference architectures for model routing, prompt versioning, observability, experimentation, and safe production rollout.
• Establish LLM/agent evaluation frameworks — offline evals, regression suites, trace diagnostics, and quality metrics tied to business outcomes.
• Own full feature development across design, implementation, testing, shipping, and servicing.
• Write and review clean, high-quality code with a focus on performance, scalability, and maintainability.
• Set best practices for AI tooling, service observability, alerting, and incident response.
• Mentor engineers across the team and foster a culture of technical excellence and continuous learning.
• Use AI tools in your daily workflow and advocate evolving best practices to the broader team.

Skills

Distributed systems

Generative AI

Agent frameworks (LangChain,L lang?0)

Frontend and backend integration

Mentoring engineers

Education

BS/MS/PhD in Computer Science or Engineering

Tools

LangChain

LangGraph

AutoGen

OpenAI API

Vector search

Job description

• Architect and build enterprise-grade Generative AI applications combining LLMs, retrieval, structured data, orchestration, and workflow automation.
• Design agentic systems and multi-step reasoning workflows using LangGraph or equivalent — with clear control over state, memory, tool invocation, and human-in-the-loop checkpoints.
• Build fault-tolerant orchestration for long-running AI workflows using Temporal or similar platforms.
• Drive reference architectures for model routing, prompt versioning, observability, experimentation, and safe production rollout.
• Establish LLM/agent evaluation frameworks — offline evals, regression suites, trace diagnostics, and quality metrics tied to business outcomes.
• Own full feature development across design, implementation, testing, shipping, and servicing.
• Write and review clean, high-quality code with a focus on performance, scalability, and maintainability.
• Set best practices for AI tooling, service observability, alerting, and incident response.
• Mentor engineers across the team and foster a culture of technical excellence and continuous learning.
• Use AI tools in your daily workflow and advocate evolving best practices to the broader team.

Required Qualifications

• 15+ years of experience building large-scale distributed systems, platforms, or enterprise applications.
• Proven track record shipping production AI/LLM-powered applications — agentic workflows, RAG systems, or intelligent automation.
• Deep expertise in Generative AI: LLMs (OpenAI), Prompt Engineering, RAG, vector search, and AI agent orchestration.
• Hands‑on experience with agent frameworks: LangChain, LangGraph, AutoGen, or equivalent.
• Frontend and backend background to integrate AI solutions end-to-end into existing applications.
• Strong software engineering fundamentals: system design, algorithms, testing, debugging, and code review.
• Demonstrated ability to lead technical direction and mentor engineers.
• Comfort in ambiguous, fast-moving problem spaces where best practices are still emerging.
• BS, MS, or PhD in Computer Science, Engineering, or equivalent practical experience.