AI Engineer, Agents and Evaluation

Pronoia Energy is a pioneering deep tech startup at the forefront of quantum energy storage innovation. As a lean, mission-driven team, we thrive on rapid prototyping, cross-disciplinary collaboration, and solving complex engineering challenges to turn quantum physics into practical, scalable products. Our current focus is developing groundbreaking room-temperature macroscopic quantum energy storage technology that promises orders of magnitude greater energy density, faster charging, and higher power delivery—while being cheaper and safer than existing battery technology. This represents a paradigm shift in energy storage with applications spanning consumer electronics, electric vehicles, renewable grids, and beyond.

About the role

To meet our ambitious goals, we are building an internal, grounded, agentic AI system that accelerates our research. We are hiring an AI Engineer to build two critical components: the orchestration layer that plans and routes work, and the verification layer that ensures the system only states what it can support. This is a founding, high-leverage role where you will own the part of the stack that decides what counts as true before the team acts on it.

You will build the agent orchestrator that decomposes a research question into steps and routes each step to the right tool. You will also create the first verification gate and evaluation harness to catch unsupported claims before they propagate. A defining rule of the system is that factual questions must go to retrieval, computational questions must go to tools, and nothing is answered from the model's own memory. You will stand up a self-hosted open-weights model on our hardware and build the entire agent loop around it. This is a founding generalist role, and early on, you will wear multiple hats across orchestration, serving, and evaluation. The role is onsite in Torrance, California.

Responsibilities

• Build the agent orchestrator and the tool-routing logic at the heart of the system.
• Stand up and serve a self-hosted open-weights model on local hardware.
• Build the first verification gate and evaluation harness, making grounding mechanical rather than hopeful.
• Enforce strict routing so claims trace to a retrieved source or a deterministic computation.
• Wear several hats as a founding generalist and later hand specialties to dedicated hires.

Requirements

• A track record of shipping a real agent or tool-use system in production, not just a demo.
• Genuine experience self-hosting open-weights models on your own GPUs, not only calling a hosted API.
• A habit of treating hallucination and tool-misuse as engineering problems with mechanical fixes.
• Builder-generalist range across orchestration, model serving, and evaluation.
• A self-starter who thrives amid ambiguity and rapid iteration.

Preferred Qualifications

• A scientific or physics background that makes our zero-fabrication standard second nature.
• Contributions to open-source serving or agent tooling such as vLLM, TGI, or agent frameworks.
• Experience building retrieval-augmented systems and evaluation suites.
• Prior work in deep tech R&D alongside interdisciplinary teams.

Benefits

• Chance to solve one of the world's biggest engineering challenges and pioneer quantum energy storage.
• Competitive salary, equity in a transformative startup, and performance-based incentives.
• Access to cutting-edge labs, tools, and resources in a flexible, collaborative work environment.
• Comprehensive benefits: health insurance, unlimited PTO, professional development stipend, and relocation assistance if needed.
• A culture of innovation where your work will accelerate our path to market impact.