About the Position

We're hiring a full-stack engineer to join our team and work on AiOn, our agentic AI platform. The scope covers the whole product: the UI operators use, the agent and prompt design behind it, the Python services, and the AWS infrastructure they run on. From floor-level to supervisors to C-suite executives at Fortune 500s, our agentic AI platform connects the systems of record with places of action in some of the most demanding operational environments.

AiOn is already live in hundreds of warehouses and factories, so the work splits roughly evenly between new features and making what exists faster, more reliable, and more extensible. We integrate frontier models from multiple providers rather than train our own, so the engineering is in the product around them. We work from first principles and ship the simplest thing that solves the problem, then refine it.

Responsibilities

• Ship and evolve full-stack features from UI through API to agent logic
• Build and extend our agent framework: tool and function calling, multi-step reasoning, and context management
• Build structured tool and data access over operational data with schema grounding, validation, and safe execution, and integrate the external systems agents act on
• Build evaluation and observability for quality, latency, safety, cost, and product outcomes such as task completion
• Improve reliability, robustness, and latency across a distributed, event-driven backend, and re-architect early implementations as the platform matures
• Maintain guardrails: least-privilege tool design, safe execution boundaries, fallbacks, and kill switches
• Work anywhere in the stack the problem requires: React and TypeScript UI, an Electron desktop app, streaming interfaces that stay usable while output is still partial, and Python services on AWS built around async and event-driven patterns

Requirements

• 5+ years building production full-stack or backend software, or a track record demonstrating equivalent depth
• Recent hands-on experience integrating LLMs into user-facing production applications
• Shipped a user-facing agentic or LLM-powered feature and owned it across the full stack
• Built evaluation harnesses for non-deterministic systems
• Track record of improving reliability, performance, and maintainability of production systems
• Strong Python and TypeScript/React, both used daily
• Built agent orchestration, or deep experience with a framework and its tradeoffs
• REST API and service design, plus async and event-driven patterns (queues, streaming, WebSockets)
• Production experience deploying and running services on AWS
• Product judgment for user-facing AI, including iterating from operator feedback and handling uncertain output well
• Fluent with agentic coding tools (Claude Code, Codex, Cursor, or similar)

Preferred Qualifications

• Tool and system integration for agents (e.g. MCP)
• Sandboxing and safe execution of untrusted code
• LLMOps or AgentOps tooling and CI/CD for AI systems
• Streaming and WebSocket patterns for real-time or long-running tasks
• Data-ingestion pipelines and multi-store data consistency
• Logistics, supply chain, or physical-operations domain experience

What This Role Is Not

• Not a prompt-only role wrapping a model API, and not demo-ware. This runs in production for enterprise customers.
• Not frontend-only or backend-only. You own the full path.
• Not greenfield-only. Much of the impact is hardening, optimizing, and re-architecting a platform already in production.

Benefits

Work with some of the most ambitious and intense people you can be around. Predominantly located in New York and Chicago, but remain open to remote employees. Compensation is commensurate with experience and is estimated to range from $160,000 to $250,000. The role is eligible for a performance-based cash bonus and equity awards.