AI Engineer

New York

Development - Back End

Permanent

Our client, a growing AI organization, is hiring an AI Engineer to join the team in New York. The successful candidate will take ownership of the tooling, AI agent infrastructure and measurement systems that enable engineering and implementation teams to deliver improvements safely, from proposing and simulating changes through to approval, deployment and evaluating results.

Responsibilities

Build internal dashboards that provide visibility into engineering delivery, platform reliability, agent activity and customer results.
Connect data from GitHub, Linear, Sentry and Grafana to uncover delivery bottlenecks, track quality and inform improvements.
Develop secure, sandboxed agents that carry out defined engineering tasks, execute tests and produce verifiable results within controlled permissions.
Create evaluation frameworks to validate agent-generated changes, control costs and improve automated delivery.
Equip implementation teams with tools to safely adjust customer settings, scheduling rules and operational playbooks.
Develop workflows for simulation, approval, verification and rollback, ensuring changes are tested, traceable and reversible.
Establish consistent, version-controlled metrics to measure engineering performance, operational efficiency and customer outcomes.
Build experimentation tools to test hypotheses, manage controlled rollouts, track exposure and assess results.
Identify recurring customer challenges and implementation fixes that could inform new features or product enhancements.
Collaborate with customers, implementation specialists and engineers to prioritize development and communicate the purpose, impact and results of changes.

Skillset

Strong TypeScript backend development skills, with experience building and supporting production services.
Hands-on experience delivering AI agents in production, covering tool design, evaluation, sandboxing, permissions and cost control.
Experience improving developer productivity through engineering metrics, internal tools or delivery processes.
A solid understanding of production reliability, access controls, audit trails and safe, reversible operational changes.
Experience with experimentation, feature flags and controlled rollouts, including measuring the impact of changes.
Strong product judgement, with the ability to turn customer needs and operational challenges into practical software.
Experience developing platform tooling or integrations with systems such as GitHub, Linear, Sentry or Grafana.
The ability to own projects from problem definition through development, deployment and ongoing improvement.
Clear communication skills, with confidence collaborating directly with customers, engineers and business stakeholders.
Customer implementation, solutions engineering or forward-deployed experience, ideally within field services, logistics or operational software.