Founding Applied ML Engineer

You'll build the core intelligence behind our agents (reasoning, planning, tool use, memory, grounding, and evaluation) across chat, voice, and computer-use interfaces. This is a founding-level, high-ownership role: you'll work directly with the founders and customers, shape the technical direction, and ship systems that run in a high-stakes, regulated environment.

Responsibilities:

• Design and build reasoning and planning systems for real production workflows.
• Build tool orchestration, grounding, and execution frameworks that hold up against messy real-world systems.
• Develop memory, context, and state management for long-running, multi-step tasks.
• Build evaluation systems that measure correctness, reliability, and performance.
• Make chat, voice, and UI-based agents work together dependably.
• Turn research ideas into production systems.
• Help define engineering culture, standards, and technical direction.

Requirements:

• 5+ years of software engineering, with strong backend / distributed systems fundamentals.
• 2+ years building and shipping LLM or agentic systems in production (real users, not POCs).
• Hands-on experience with evals, retrieval, memory, and grounding for LLM systems.
• Strong knowledge of Python
• Comfort with ambiguity and a bias toward reliable, measurable, testable systems.
• Product sense: you care about real users and real outcomes.
• Clear communication and strong collaboration.