Artificial Intelligence Engineer

iT Resource Solutions.net,inc; New York (NY); On-site; USD 170,000 - 210,000; Full time

Job summary

iT Resource Solutions.net,inc is seeking a highly skilled Agentic AI Engineer to design, build, and deploy production-grade AI systems that autonomously execute complex business workflows. The role focuses on LLM-based agents, RAG, multi-agent systems, backend and full-stack AI product development, with emphasis on reliability, observability, and secure integration with enterprise systems.

You will work with Python, FastAPI, React, and cloud platforms to deliver scalable AI applications and

Qualifications

• Proven experience building production-grade AI systems with autonomous workflows.
• Strong background in LLM-based agents and RAG pipelines.
• Experience integrating LLMs with backend APIs and event-driven architectures.
• Knowledge of AI observability, guardrails, and security in enterprise apps.

Responsibilities

• Design and architect production-grade Agentic AI systems capable of reasoning, planning, and executing business workflows.
• Build LLM-powered agents and multi-agent workflows using modern AI frameworks and orchestration patterns.
• Develop scalable RAG pipelines including document ingestion, embedding, vector search, retrieval, ranking, and contextual generation.
• Integrate LLMs with enterprise systems through backend APIs, tools, function calling, and event-driven architectures.
• Build AI applications using OpenAI and other foundation models, optimizing prompts, agent behavior, and tool usage.
• Develop reliable AI systems with memory, evaluation, observability, guardrails, security, and human-in-the-loop workflows.
• Architect and develop backend services using Python and FastAPI.
• Build full-stack AI products and internal platforms using React and TypeScript.
• Design event-driven and asynchronous workflows to support autonomous AI agents at scale.
• Implement semantic and vector search using Pinecone and FAISS.
• Develop AI/ML systems for fraud detection, risk scoring, anomaly detection, compliance automation, and intelligent business operations.
• Establish evaluation frameworks and monitoring systems to measure agent accuracy, reliability, latency, cost, and production performance.
• Deploy and operate AI applications using AWS, Docker, Kubernetes, and modern MLOps practices.
• Collaborate with product, engineering, data, and business teams to identify AI-driven automation opportunities.

Job description

Job Description

We are seeking a highly skilled **Agentic AI Engineer / Applied AI Engineer** to design, build, and deploy production-grade AI systems that go beyond conversational experiences and execute complex business workflows autonomously.

The ideal candidate will have strong experience in **LLM-based agents, Retrieval-Augmented Generation (RAG), multi-agent systems, AI automation, backend engineering, and full-stack AI product development**. This role requires the ability to translate complex user intent into reliable, scalable, and observable automated actions.

Key Responsibilities

• Design and architect **production-grade Agentic AI systems** capable of reasoning, planning, decision-making, and executing business workflows.
• Build **LLM-powered agents and multi-agent workflows** using modern AI frameworks and orchestration patterns.
• Develop scalable **RAG pipelines**, including document ingestion, embedding, vector search, retrieval, ranking, and contextual generation.
• Integrate LLMs with enterprise systems through **backend APIs, tools, function calling, and event-driven architectures**.
• Build AI applications using **OpenAI and other foundation models**, optimizing prompts, agent behavior, context management, and tool usage.
• Develop reliable AI systems incorporating **memory, evaluation, observability, guardrails, security, and human-in-the-loop workflows**.
• Architect and develop backend services using **Python and FastAPI**.
• Build full-stack AI products and internal platforms using **React and TypeScript**.
• Design event-driven and asynchronous workflows capable of supporting autonomous AI agents at scale.
• Implement semantic and vector search solutions using technologies such as **Pinecone and FAISS**.
• Develop AI/ML systems for areas including **fraud detection, risk scoring, anomaly detection, compliance automation, and intelligent business operations**.
• Establish evaluation frameworks and monitoring systems to measure **agent accuracy, reliability, latency, cost, and production performance**.
• Deploy and operate AI applications using **AWS, Docker, Kubernetes, and modern MLOps practices**.
• Collaborate with product, engineering, data, and business teams to identify opportunities for **AI-driven automation and intelligent workflows**.

Required Technical Skills

• **Python**
• **OpenAI / LLM APIs**
• **LangChain**
• **LangGraph**
• **LangSmith**
• **Vector databases and semantic search**
• **Pinecone / FAISS**
• **FastAPI**
• **REST APIs and backend development**
• **React / TypeScript**
• **Redis**
• **AWS**
• **Docker**
• **MLflow**
• AI/ML evaluation and observability
• Agent orchestration and tool/function calling
• Event-driven architectures and workflow automation

Preferred Experience

• Experience building **Agentic AI platforms or autonomous AI workflows** in production.
• Experience with **financial services, fraud detection, risk management, compliance, or enterprise automation**.
• Strong understanding of **LLM reasoning, retrieval, memory, planning, tool use, and agent evaluation**.
• Experience taking AI products from **prototype/MVP through production deployment and ongoing optimization**.
• Experience building scalable, secure, and reliable **enterprise AI applications**.

Target Roles

This position is suited for professionals working in or transitioning toward:

• **Agentic AI Engineering**
• **AI Automation Engineering**

Ideal Candidate Profile

The ideal candidate combines **AI/ML expertise with strong software engineering and product development skills**. You should be comfortable moving from an AI architecture concept to a working production system, building the underlying APIs and infrastructure, integrating LLMs and retrieval systems, and implementing the monitoring and guardrails necessary to make autonomous AI reliable in real-world enterprise environments.