Senior Engineer, AI/ML

A2Z Sync•Denver, CO
•$160,000 - $180,000•Hybrid

About The Position

A2Z Sync is hiring a hands-on Senior Engineer, AI/ML to build and operate production agentic AI systems for its multi-tenant automotive SaaS platform. The platform serves thousands of dealer groups and runs on AWS serverless services. Agents will connect to production systems, work with real dealer data, and execute workflows that can affect dealer revenue and money. The role focuses on production agents, tool integrations, evaluations, guardrails, cost and latency management, and observability. The engineer will build agent logic and multi-agent workflows using code-first frameworks such as Strands or LangGraph, deploy them on AWS Bedrock AgentCore, and create Python tools, MCP servers, and Gateway targets for safe access to production APIs. They will establish evaluation pipelines and CI gates, implement approval and rollback paths, and instrument the systems they ship. This is primarily a coding role, with design work within established platform patterns and collaboration with Tech Leads. The engineer is expected to understand the dealer workflows and business value behind each solution, and to use evidence and judgment to choose a simpler deterministic tool—or no agent—when that better serves the customer. The position is based in Denver, Colorado, with a hybrid option requiring two days per week in the office, or may be fully remote elsewhere in the United States. It is full-time and reports to the Head of Data Platform.

Requirements

  • At least 5 years of software engineering experience.
  • Hands-on production experience building LLM agents in a code-first framework. Strands Agents, LangGraph, Google ADK, OpenAI Agents SDK, or a comparable framework is acceptable.
  • Strong Python skills and the ability to read and contribute to Java Spring Boot services.
  • Hands-on experience with AWS serverless services, including Lambda, EventBridge, DynamoDB, and Step Functions.
  • Experience with prompt engineering, tool or function-calling design, and evaluating LLM output quality in production.
  • Business-conscious judgment: start from the problem and its value, and demonstrate having chosen a simpler solution over a more complex one when it better served the customer.
  • Interest in a heads-down building role focused primarily on shipping code.

Nice To Haves

  • Direct experience with Strands Agents and/or AgentCore Runtime, including migrating agent workloads from Lambda or Fargate to a managed agent runtime.
  • Experience with LLM-as-judge evaluation, agent-to-agent orchestration, or agent governance.
  • Direct production experience with MCP servers.
  • Experience owning production observability using OpenTelemetry and CloudWatch.
  • Automotive, fintech, or multi-tenant marketplace platform experience.
  • Familiarity with Bedrock Guardrails, model cost and latency optimization, and multi-agent orchestration patterns.
  • Experience with data pipelines such as Glue or Athena, or ETL and data lake tooling.

Responsibilities

  • Build and operate production agents on AWS Bedrock AgentCore, including agent logic, tool orchestration, and multi-agent workflows.
  • Develop framework-agnostic Python tools, MCP servers, and AgentCore Gateway targets that enable agents to call production APIs safely.
  • Create offline and online evaluation pipelines and LLM-as-judge CI/CD gates to detect regressions.
  • Implement guardrails, approval gates, and rollback paths to ensure safe failure behavior.
  • Track per-agent costs and manage latency, including multi-model routing so workflows deliver value relative to their costs.
  • Instrument production agents with AgentCore session tracing, OpenTelemetry, and CloudWatch dashboards.
  • Learn the platform architecture, existing agents, integration surfaces, and dealer workflows; deliver a first production tool integration during the first month.
  • Own agent workflows end to end, from design through production, including agent logic, tools, evaluations, CI gates, and guardrails.
  • Ship new agents and tools autonomously, with observability and cost tracking for each system owned.
  • Assess dealer problems and business value before selecting a technical solution, including recommending deterministic tools or no agent when appropriate.
  • Work within established architectural patterns and collaborate with Tech Leads whose domains the agents affect.
  • Use Claude as a development partner for agent code, tool schemas, and prompt iteration.

Benefits

  • Base salary of $160,000–$180,000 depending on experience and qualifications, plus an equity grant.
  • Employer-paid health, dental, and vision insurance for employees and their families, starting on day one.
  • Flexible work arrangement: Denver hybrid with two days per week in the office or fully remote anywhere in the United States.
  • 401(k) retirement plan with company match.
  • Unlimited paid time off and 10 paid holidays.
  • Employer-paid short-term and long-term disability coverage.
  • Employer-paid life and AD&D insurance.
  • Confidential therapy sessions through BetterHelp.
  • Pet insurance options.
  • Voluntary identity theft protection services.
  • On-site gym in Denver.
  • Stocked kitchen with snacks and beverages.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service