Photonic AI Modelling & Simulation Architect

Lumai; Oxford; On-site; GBP 110,000 - 160,000; Full time

Job summary

Lumai, an Oxford-based optical compute company, seeks a Senior Modelling Engineer to own performance and power modelling for AI hardware. You’ll build a Python-based framework, model compute engines, memory, interconnects and accelerator blocks across device configurations, aligning predictions with RTL or emulation results to guide architecture decisions.

You’ll lead with CI/CD pipelines, ingest MLIR outputs from multiple compiler flows, and translate findings into actionable direction for the

Qualifications

• Proven experience building or substantially extending a hardware/software performance modelling or simulation framework for AI/ML accelerators.
• Strong understanding of hardware concurrency, event-driven modelling and AI inference accelerator micro-architecture.
• Hands-on experience characterising AI operators and correlating model predictions with real hardware or hardware-accurate reference data.
• Familiarity with compiler internals and intermediate representations such as MLIR, including tooling that consumes compiler output to drive simulation.
• Strong software engineering and technical leadership practice: framework design, CI/CD ownership, and direction or review of junior engineers' or interns' work.

Responsibilities

• Design, build and maintain a Python-based framework that models hardware and software latency, hardware concurrency and event-driven relationships.
• Model compute engines, interconnect and synchronisation fabric, memory and bridge interfaces, and accelerator blocks across device configurations.
• Characterise convolution, depthwise convolution, pooling, attention and other operator workloads against hardware, RTL or emulation results.
• Build compiler-agnostic interfaces that ingest compiled models and MLIR from multiple internal compiler flows.
• Analyse simulation traces with the architecture and compiler teams to improve layer-to-hardware mappings and resolve performance discrepancies.
• Run industry benchmarks and representative models - UL Procyon, Geekbench AI, Stable Diffusion and contemporary LLMs - to produce decision-ready KPIs.
• Develop block-level power models and validate worst-case power scenarios with the micro-architecture, verification and physical-design teams.
• Own the CI/CD pipelines and simulation flows that keep results reliable and reproducible as usage scales.
• Translate modelling findings into architecture and compiler decisions, setting technical direction and developing engineers or interns as the team grows.

Skills

Python

Performance modelling

AI accelerator architecture

CI/CD ownership

Leadership

MLIR familiarity

Hardware concurrency

Tools

MLIR

CI/CD

RTL emulation

Job description

Lumai, an Oxford-based optical compute company, seeks a Senior Modelling Engineer to own performance and power modelling for AI hardware. You’ll build a Python-based framework, model compute engines, memory, interconnects and accelerator blocks across device configurations, aligning predictions with RTL or emulation results to guide architecture decisions.

You’ll lead with CI/CD pipelines, ingest MLIR outputs from multiple compiler flows, and translate findings into actionable direction for the