Senior AI/ML Engineer for Production Agent Systems

A2Z Sync, Inc.; Northern (KY); Hybrid; USD 160,000 - 190,000; Full time

Benefits offered by this job

Medical, dental, vision benefits

STD/LTD and life insurance

401k with employer matching

Unlimited PTO and holidays

Job summary

A2Z Sync in the United States seeks a hands-on software engineer to build production agents for our automotive SaaS platform. You will write code focusing on agent logic, tool orchestration, and multi-agent workflows on AgentCore Runtime.

Proficiency in Python and familiarity with Java (Spring Boot) are valued, as is experience with AWS serverless services like Lambda and EventBridge. You\'ll own workflows, evaluate latency, and ensure observability and cost tracking.

Qualifications

• 5+ years of software engineering experience with hands-on production work.
• Experience building LLM agents in code-first frameworks.
• Strong Python programming skills.
• Ability to read/contribute to Java (Spring Boot) services.
• Experience with AWS serverless (Lambda, EventBridge, DynamoDB, Step Functions).

Responsibilities

• Build production agents in AgentCore: agent logic, tool orchestration, and multi-agent workflows.
• Create framework-agnostic Python tools, MCP servers, and Gateway targets for safe production APIs.
• Develop offline/online evaluation pipelines and CI gates for regression checks.
• Implement guardrails and rollback paths for safe/robust agents.
• Manage per-agent cost, latency, and observability with monitoring dashboards.

Skills

5+ years exp

LLM agents

Python

Java Spring Boot

AWS serverless

Tools

AWS Bedrock

AgentCore Runtime

MCP servers

Job description

A2Z Sync in the United States seeks a hands-on software engineer to build production agents for our automotive SaaS platform. You will write code focusing on agent logic, tool orchestration, and multi-agent workflows on AgentCore Runtime.

Proficiency in Python and familiarity with Java (Spring Boot) are valued, as is experience with AWS serverless services like Lambda and EventBridge. You\'ll own workflows, evaluate latency, and ensure observability and cost tracking.