Agentic AI Engineer - Hybrid (Onsite/Remote)

Request Technology, LLC; Chicago (IL); Hybrid; USD 140,000 - 190,000; Full time

Job summary

Request Technology, LLC seeks an experienced software engineer to design and deploy agentic AI systems with strong Python and API skills. You will build orchestration patterns and integration for reliable, auditable workflows in a regulated setting. The role emphasizes AI risk mitigation, governance collaboration, and scalable cloud infrastructure.

We value production AI/LLM experience, cloud knowledge (AWS), and the ability to implement robust safeguards and auditability across systems.

Qualifications

• Bachelor's or Master's in a technical field; Master's preferred.
• 4-7 years of software engineering with production AI/LLM experience is ideal.
• Strong Python and SQL, plus distributed systems and API design fundamentals.
• Experience building LLM-powered applications or agentic systems.
• Familiarity with AI risk areas and data privacy concepts.
• Cloud experience (AWS preferred); comfort with Docker and CI/CD.

Responsibilities

• Own design and delivery of agentic AI systems end-to-end.
• Architect orchestration patterns, tool/context integration, evaluation pipelines.
• Own AI infrastructure on AWS and contribute to self-sufficiency.
• Implement safeguards against AI risks with governance collaboration.
• Build audit logging and human-in-the-loop checks for traceability.

Skills

Python

API design

Distributed systems

LLM/AI systems

Agent orchestration

Data privacy awareness

Prompt risk mitigation

Cloud fundamentals

Education

Bachelor's in CS/Engineering or related field

Master's preferred

Tools

Docker

CI/CD

Containerization

AWS

Claude

Anthropic API

Claude.ai/Console

Job description

Request Technology, LLC seeks an experienced software engineer to design and deploy agentic AI systems with strong Python and API skills. You will build orchestration patterns and integration for reliable, auditable workflows in a regulated setting. The role emphasizes AI risk mitigation, governance collaboration, and scalable cloud infrastructure.

We value production AI/LLM experience, cloud knowledge (AWS), and the ability to implement robust safeguards and auditability across systems.