Senior Automation Engineer

Harvey Nash Group; Chicago (IL); On-site; USD 150,000 - 210,000; Full time

Job summary

Harvey Nash Group in Chicago or New York City seeks a Senior Automation Engineer to design and govern enterprise-scale intelligent automation using Agentic AI and LLMs. You will integrate LLM APIs, RAG, and multi-agent architectures, ensuring secure, observable, and scalable AI systems.

The role combines AI engineering, automation, software engineering, and security architecture, collaborating with Security, Product, Legal, Compliance, and Operations to deliver production-ready AI capabilities.

Qualifications

• Experience building production-grade Agentic AI and Generative AI systems.
• Deep understanding of LLMs, RAG, prompt engineering, agent orchestration, and multi-agent systems.
• Strong programming experience with Python and at least one compiled language.
• Experience building scalable microservices and API-based architectures.
• Hands-on experience with CI/CD and Infrastructure as Code (IaC).
• Knowledge of AI security including jailbreak prevention, tool misuse prevention, AI threat modeling, and secure handling of model inputs/outputs.
• Experience building observable and auditable AI pipelines with logging, monitoring, and tracing.
• Ability to lead technical initiatives and influence teams without direct authority.

Responsibilities

• Design, develop, and deploy production-grade Agentic AI and intelligent automation systems.
• Build solutions leveraging LLM APIs, RAG, prompt engineering, tool/function calling, and multi-agent architectures.
• Design and implement agent orchestration patterns for complex enterprise workflows.
• Develop secure AI solutions with protections against prompt injection, jailbreaking, tool misuse, and unsafe inputs/outputs.
• Apply zero-trust principles and AI threat modeling throughout the lifecycle.
• Establish observability with logging, tracing, monitoring, and auditability for AI systems.
• Troubleshoot non-deterministic AI/LLM failures in production environments.
• Develop and support microservices, APIs, CI/CD pipelines, and Infrastructure as Code.
• Communicate architecture, risks, trade-offs, and recommendations to leadership.

Skills

Agentic AI

LLMs

Python

Security engineering

Architecture decisions

Tools

CI/CD

Infrastructure as Code

Job description

US citizens, Green Card Holders, and those authorized to work in the US are encouraged to apply. We are unable to sponsor H1b candidates at this time

Senior Automation Engineer - Agentic AI

Location: Chicago, IL or New York City, NY

Employment Type: Full-Time

Job Overview

We are seeking a Senior Automation Engineer to design, build, and govern enterprise-scale intelligent automation solutions centered on Agentic AI and Large Language Models (LLMs).

This is a senior hands‑on engineering role at the intersection of AI engineering, automation, software engineering, and security architecture. The ideal candidate will have demonstrated experience building and deploying production‑grade agentic AI systems, including LLM integrations, Retrieval-Augmented Generation (RAG), agent orchestration, and multi‑agent architectures.

The engineer will partner closely with Engineering, Security, Product, Legal, Compliance, and Operations teams to transform emerging AI capabilities into secure, observable, scalable, and resilient enterprise solutions.

Key Responsibilities

• Design, develop, and deploy production‑grade Agentic AI and intelligent automation systems.
• Build solutions leveraging LLM APIs, RAG, prompt engineering, tool/function calling, and multi‑agent architectures.
• Design and implement agent orchestration patterns for complex enterprise workflows.
• Develop secure AI solutions with protections against prompt injection, jailbreaking, tool misuse, and unsafe model inputs/outputs.
• Apply zero‑trust principles, AI threat modeling, and secure engineering practices throughout the AI development lifecycle.
• Design resilient AI systems with strong observability, logging, tracing, monitoring, and auditability.
• Troubleshoot and resolve non‑deterministic AI/LLM failures in production environments.
• Build scalable software and services using Python and at least one compiled programming language.
• Develop and support microservices, APIs, CI/CD pipelines, and Infrastructure as Code (IaC).
• Establish technical standards, architecture patterns, and engineering best practices for enterprise AI and automation.
• Partner across Engineering, Security, Product, Operations, Legal, and Compliance to drive AI initiatives from concept through production.
• Communicate technical architecture, risks, trade‑offs, and recommendations clearly to both engineering teams and senior leadership.

Required Qualifications

• Strong hands‑on experience building and deploying Agentic AI / Generative AI systems in production.
• Deep understanding of LLMs, RAG, prompt engineering, agent frameworks, agent orchestration, and multi‑agent systems.
• Strong programming experience with Python plus experience with a compiled language.
• Experience building scalable microservices and API‑based architectures.
• Hands‑on experience with CI/CD and Infrastructure as Code.
• Strong understanding of AI security, including:
• Jailbreak prevention
• Tool/function misuse prevention
• AI threat modeling
• Secure handling of model inputs and outputs
• Zero‑trust security principles
• Experience building observable and auditable AI pipelines, including logging, monitoring, and tracing.
• Strong understanding of non‑deterministic AI system behavior and failure modes.
• Demonstrated ability to lead technical initiatives and influence teams without direct authority.
• Strong communication skills with the ability to translate complex technical concepts into architecture decisions, roadmaps, risk assessments, and executive‑level recommendations.

Preferred Qualifications

• Experience performing or supporting AI red teaming, penetration testing, or adversarial testing of LLM/AI systems.
• Experience working in financial services, fintech, banking, or another highly regulated industry.
• Exposure to AI governance, responsible AI, model risk management, or enterprise AI policy development.
• Experience working with Security, Legal, Risk, and Compliance organizations on enterprise AI adoption.
• Ability to present AI architecture, security risks, technical trade‑offs, and mitigation strategies to senior leadership.