AI Engineer

We are seeking an experienced AI Engineer to architect and build LLM-powered agentic systems that form the core of our product. You will own the development of autonomous agents capable of executing multi-step tasks, building evaluation infrastructure for quality assurance, designing retrieval layers for accurate reasoning, and integrating advanced AI features into our user-facing products.

The landscape is rapidly evolving; your role involves shaping this future alongside founders rather than adhering to rigid frameworks. We value fluency in modern LLMs where you treat them as robust backend components. Whether coming from agents, RAG, evals, fine-tuning, or retrieval, what matters most is shipping reliable systems to real users.

Key Responsibilities:

• **Build Autonomous Agents:** Design and ship LLM-powered systems that execute multi-step workflows autonomously across internal tools and third-party services, knowing precisely when to delegate to human operators.
• **Own Quality & Evaluation:** Construct infrastructure measuring AI performance, detecting regressions before they impact users, and converting production signals into optimized prompts and models. We prioritize measurable quality metrics over intuition.
• **Build the Knowledge Layer:** Architect retrieval systems for agent reasoning while ensuring knowledge remains accurate, versioned, and synchronized with dynamic external sources.
• **Integrate AI Products:** Deploy copilots and assistive features that significantly enhance user speed and efficiency through sound judgment on model autonomy versus human assistance.
• **Production Readiness & Iteration:** Deploy systems to production environments, monitor real-world behavior, and implement rapid improvements based on actual usage patterns rather than theoretical timelines.
• **Strategic Roadmapping:** Partner with founders to define the technical roadmap. Provide expert insights into current model capabilities versus limitations to make informed bets on emerging technologies.
• **Scalable Architecture:** Make architectural decisions that sustain growth by orders of magnitude, building robustly for future engineering teams and scale requirements.

Requirements:

• **Proven Production Experience:** A track record of shipping LLM-powered agents or systems to production environments handling real user traffic, not just demos.
• **Comprehensive AI Fluency:** Ability to reason concretely about prompting strategies, tool use patterns, context management, retrieval architectures, latency optimization, cost control, and failure mode analysis.
• **Data-Driven Quality Engineering:** Experience building evaluation frameworks, designing metrics, capturing production signals, and systematically using data to improve model quality.
• **Reliability in Production:** Proven ability to monitor, debug, and maintain AI systems under load where real people depend on consistent performance.
• **Strong Software Fundamentals:** Solid coding standards ensuring your work is easily maintained by others; you take ownership of what you ship.
• **Comfort with Ambiguity:** Thriving in undefined spaces without a pre-existing playbook. You are excited to build the framework as we go, bringing creativity and technical rigor together.