Software Engineer, AI Platform (New York City Metropolitan Area)

What if an AI agent could tell an engineer exactly why a system failed?

That’s what you’ll help build.

We’re working with a high-growth technology company sitting at the intersection of AI, software and complex physical systems.

Their platform already captures huge volumes of telemetry, time-series data, test results and engineering logs. Now they’re building intelligent agents capable of reasoning across that data - helping engineers investigate failures, spot anomalies, compare test runs and get answers from incredibly complex systems faster.

They’re looking for an experienced software engineer who has already built AI or agent systems in production and wants the ownership of taking something genuinely new from 0→1.

What You’ll Build

• Production AI agents and agentic workflows used to solve real engineering problems.
• Retrieval and context systems capable of reasoning across complex technical data.
• Infrastructure for agent evaluation, observability and reliability.
• Backend and distributed systems supporting AI workloads at scale.
• AI capabilities that can investigate failures, compare test runs and identify anomalies across large datasets.
• Rapid prototypes that you’ll test with real users and turn into production features.
• Evaluation frameworks for measuring agent quality, accuracy and performance.
• You’ll have significant ownership, working directly with engineers and customers to understand difficult problems and take solutions from idea → prototype → production.

What We’re Looking For

• 5+ years of software engineering experience , particularly backend or distributed systems.
• Hands-on experience building AI/agent systems running in production .
• Experience with LLM applications, agent infrastructure, retrieval/context systems, evaluation or AI reliability.
• Strong engineering fundamentals - this is an engineering-first AI role , not a research position.
• Experience working with large-scale data, APIs and distributed systems.
• Comfortable making architectural decisions in an ambiguous 0→1 environment .
• Strong product instincts and experience working closely with users.
• A track record of owning complex systems beyond simply integrating an LLM API.

If this sounds like you, please apply with your latest CV and we will be in touch to discuss the role further.