Lead Engineer, LLMs

About Atomic Tessellator

Atomic Tessellator is building a sovereign future by empowering companies and nations to achieve materials breakthroughs, enhance product performance, and secure supply-chain independence. They do this through the development of the most powerful first-principles simulation platform for engineering materials research.

As a seed-stage company with a headcount of five, and just over a year in operation, Atomic Tessellator has already:

• Built a distributed worker architecture to modularise computational materials science operations.
• Scaled machine-learned interatomic potential (MLIP) models to enable multi-GPU inference, modeling up to 700,000 atoms.
• Completed pilot projects across aerospace, defence, nuclear fusion, and advanced polymers.
• Discovered (and are in the process of patenting) two materials, including a high-temperature rare earth magnet substitute.

Their operational philosophy emphasizes speed and a bias-to-action, constantly error-correcting and balancing explore/exploit strategies.

About the Role: Lead Engineer, LLMs

Atomic Tessellator operates as a virtual lab, capable of discovering new materials entirely through simulation. With the foundations established, the current goal is to make this system recursively exponential. As a Lead Engineer, LLMs, you will be crucial in accelerating materials discovery pipelines and advancing the platform.

Your responsibilities will include:

• Building a system to replicate materials research experiments from papers within Atomic Tessellator.
• Automating the creation of materials research pipelines, working at the intersection of language models and materials AI.
• Taking complete ownership of LLM-facing interfaces (e.g., CLI or MCP), with your decisions guiding the design.
• Accessing unlimited LLM credits from providers of your choice.
• Collaborating closely with scientists for hypothesis generation and validation.
• Developing internal tooling and coding development workflows for the entire team, requiring familiarity with concepts like loops and frequent intentional compaction.

Given the rapid and chaotic developments in the LLM space, you should be able to discern enduring trends and build solutions positioned for future advancements.

This is an open-ended role, and while specific experience isn't the primary focus, a demonstrated "hacker trait" through past projects is highly valued.

Key skills/competency

• Large Language Models (LLMs)
• Material Science
• AI/Machine Learning
• Computational Materials Science
• Distributed Systems
• Python Programming
• Workflow Automation
• Interface Design (CLI/MCP)
• Hypothesis Generation
• Problem Solving