Staff Software Engineer, Agentic Platform

We're looking for an experienced Staff Software Engineer to help architect and scale the agentic systems at the core of the Axion platform. This is a senior individual contributor role: you'll own design decisions that determine how our agents reason, act, and integrate with enterprise data, working in close partnership with Engineering and Product leadership.

The hard problem is the data—customer, service, field, telematics, warranty, and aftermarket signals that are disconnected and mostly unstructured—and the bar is high, because an agent's conclusion can drive a recall or a redesign. The ideal candidate thrives in early stage companies, has deep experience building complex, data-intensive systems, and knows what it takes to make non-deterministic, LLM-driven systems reliable in production.

- Own technical architecture for our agentic systems—orchestration, tool use, memory, retrieval, evaluation, observability, and the guardrails that keep agents reliable when the input data is noisy and incomplete.

- Build and harden the reasoning layer and infrastructure that take customer data from ingestion through agent-driven reasoning to root-cause insight, at the scale and reliability manufacturers require.

- Establish rigorous evaluation and testing for non-deterministic systems—measuring agent accuracy against expert-validated ground truth and the outcomes customers track: detection rates, investigation speed, and warranty cost.

- Partner across Engineering and Product to shape the technical vision and roadmap for the agent platform.

- Raise engineering standards through code review, design docs, and the technical direction others build on.

- Mentor engineers on agentic patterns and system design, unblocking hard problems and sharing context generously.

- Minimum 7+ years of software engineering experience, with recent, hands-on focus on building agentic systems (LLM orchestration, tool/function calling, multi-step and multi-agent reasoning, retrieval and context engineering, and interoperability protocols such as MCP, or comparable work).

- Demonstrated ability to design and own complex distributed systems, ideally in data-intensive B2B SaaS environments.

- Hands-on fluency with the modern agentic stack and a strong intuition for the failure modes of non-deterministic, LLM-driven systems—plus the evaluation and observability practices needed to tame them.

- Experience turning messy, heterogeneous real-world data into something a model can reason over reliably.

- A track record of technical mentorship; you make the engineers around you better without needing formal authority.

- A firm believer in a "Data First" philosophy who can make sound decisions in ambiguous, fast-moving situations.

- A strong executor in fast-paced environments who can balance shipping MVPs with a commitment to production-grade systems.