Senior AI Engineer

POSITION SUMMARY:

We are looking for a Senior AI Engineer to build the systems that make AI agents do real, reliable work across our client’s company. This is a deep, hands-on, senior individual-contributor role. You will own the implementation of their agentic platform — the harness, the agent pipelines, the evaluation infrastructure, and the production systems that turn AI from a prototype into something teams depend on every day.

By "harness" we mean the machinery that makes autonomous AI reliable: the orchestration loop, the tool and data integrations, the testing and evaluation gates, the observability layer, and the deployment infrastructure around the models. Building that machinery — and keeping it running in production against real data and real workflows — is the job.

This is not a role at a software company, and it is not a role where you write a little code on the side. It is a role building the foundation an entire organization will run AI on for the next decade. The portfolio is messy, the problems are real, and the mandate is clear.

KEY JOB RESPONSIBILITIES:

Build the harness. Implement the core machinery that makes AI agents reliable: the orchestration loop, the tool-execution and integration layer, evaluation gates, state persistence, error recovery, and the observability that makes agent behavior legible. The models change; the harness you build is what lasts.

Ship agentic systems to production — and keep them reliable. Take AI systems from prototype to production: deployment, monitoring, rollback, controlled release, and the self-healing loops that detect and recover from failures. The bar is not a demo — it is autonomous systems running against real client data and workflows, reliably, with you accountable for correctness and uptime.

Build the evaluation and verification infrastructure. Verification is what separates a demo from production. You will build the evaluation harness, the regression suites, the deterministic gates (tests, linters, contract checks), and the automated judging infrastructure that lets them prove AI output is correct before it ships.

Build the platform substrate. Implement the production components that connect AI agents to our client’s real systems and data — Autodesk, SAP, Databricks, and a growing set of external services — and the interfaces people use to work with those agents.

Set the engineering bar by example. As one of the most senior engineers on the team, you set the implementation patterns, write the reference code others build on, review at depth, and raise the quality of everyone working alongside you.

REQUIRED KNOWLEDGE, EDUCATION, EXPERIENCE, SKILLS, AND ABILITIES:

• 10+ years in software engineering, with demonstrated depth as a senior individual contributor who ships complex systems to production
  
• Hands-on experience building and operating production AI or agentic systems — not just using AI tools in your own workflow. You have taken an LLM or agent-powered system to production and kept it running
  
• Experience implementing the components behind reliable AI systems: orchestration, tool/function calling, evaluation, context management, and handoffs between steps or agents
  
• Strong software engineering fundamentals — testing, CI/CD, observability, error handling — applied to the realities of nondeterministic AI systems
  
• Production cloud operations, ideally AWS: architecting, deploying, and operating real workloads
  
• Data and integration experience: building pipelines that move data reliably between enterprise systems (ERP, SaaS APIs, data warehouses or lakehouses)
  
• A pragmatic builder's instinct: you build the reusable thing, iterate in production, and know when shipping behind a flag beats perfecting on paper
  
• Strong communicator who can work with engineers, managers, and executives and adjust the level for each
  
  

NICE TO HAVE:

• Hands-on experience with an agent framework or SDK and with multi-agent or planner/generator/evaluator architectures
  
• Experience building evaluation frameworks or automated AI-judging systems
  
• Experience with Databricks or a similar lakehouse platform
  
• Experience building tool-integration layers (e.g., MCP servers) between AI systems and enterprise applications
  
• Experience in a non-software-company engineering organization — internal tools, corporate IT transformation, or similar
  
• Open-source contributions or public work that shows how you build
  
  

WHY THIS ROLE:

You will build the platform an entire organization runs AI on, with a clear mandate and a direct line to the Director of APEX. The platform is early — that is the appeal. You are not maintaining someone else's infrastructure; you are building the harness our client will use for the next decade. When the models get better, the infrastructure you build is what lets the company capture it.