Lead Engineer, LLMs

About Atomic Tessellator

Atomic Tessellator is the computational infrastructure for advanced materials, enabling defence and aerospace organisations to rapidly model, test, and optimise materials under extreme constraints.

Our mission is to remove the materials bottleneck so civilisation can advance at the speed of compute.

We're a seed-stage company with a headcount of five, and have been around for a little over a year. In this time, we have:

• Built a distributed worker architecture to modularise computational materials science operations.
• Scaled machine-learned interatomic potential (MLIP) models to enable multi-GPU inference, letting us model 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, one of which is a high-temperature rare earth magnet substitute.

Everything modern depends on advanced materials, but materials development remains slow, expensive, and heavily constrained by physical trial and error.

Atomic Tessellator is building a CAD-style simulation engine for materials discovery: computational infrastructure that lets organisations design, model, test, and optimise materials before committing to costly real-world experimentation.

We're building a validated predictive engine and deploying it as secure infrastructure for teams that need reliable answers under real operational constraints.

Materials resilience underpins industrial sovereignty and defence readiness. The organisations that can model and deploy advanced materials fastest will shape the next generation of strategic capability.

About the role

We're seeking a Lead LLM engineer to help accelerate our materials discovery pipelines and take our platform to the next level.

Your role will focus on building systems that can replicate experiments from materials research papers within the Atomic Tessellator platform, and automate the creation of materials research pipelines through agentic means. You'll be working at the frontier of language models and materials AI.

This is a lead role, but not a blank-sheet strategy role. We're looking for someone who can take direction well, retain the full map of a complex system in their head, and then drive execution with strong taste and high standards.

• You'll lead the implementation of our LLM-facing systems and interfaces.
• You'll build internal tooling and development workflows for the broader team.
• You'll work closely with our scientists to support hypothesis generation and validation.
• You'll have access to effectively unlimited LLM credits across the providers you think are best suited to the job.

At a minimum, you should be comfortable with:

• Designing reliable multi-step and tool-using LLM systems.
• Understanding prompt and context architecture, tool-calling, context poisoning, and long-context degradation.
• Making sound trade-offs between MCP, CLI, and other integration standards.
• Building greenfield systems such as long-running tasks, subagents, loops, and orchestration layers.
• Creating engineering backpressure around these systems through tests, evals, instrumentation, and operational safeguards.
• Working effectively in brownfield codebases: research, plan, implement, and keep momentum without losing quality.
• Thinking clearly about infrastructure and environment design, including git worktrees, dev containers, and security considerations.

More broadly, we're optimising for strong engineers.

We're looking for people who:

• Understand systems deeply and can retain a working map of complex software in their heads.
• Write clean software with good abstractions, readable code, sensible interfaces, and pragmatic operational judgment.
• Can take ambiguous technical goals, ask the right questions, and turn them into robust implementations.
• Are able to see past fast-moving trends in the LLM space and build for the underlying ground truths.

We care less about whether you've spent years working in "LLMs" specifically, and more about whether you're an exceptional engineer with evidence of taste, judgment, and the ability to build hard things quickly.