AI Inference Engineer — Equity Sign-On + High-Throughput Serving

Fuse Energy Supply; Greater London; On-site; GBP 63,000 - 103,000; Full time

Benefits offered by this job

Equity sign-on bonus

Biannual bonus

Fully expensed tech

Breakfast and dinner allowance

Job summary

Fuse Energy seeks a founding engineer to define and build our inference serving stack, driving architecture decisions for high-throughput, low-latency workloads. You will own model-level optimisation strategies, including quantisation and speculative decoding, and collaborate with CUDA/GPU teams to integrate performance work.

The role reports directly to the CTO in a pioneering energy-AI platform, with equity and competitive compensation in a fast-growing startup environment.

Qualifications

• 4+ years of experience building or operating large-scale inference serving systems.

Responsibilities

• Define our inference serving strategy and architecture from first principles.

Skills

Inference serving

GPU/CUDA collaboration

System architecture

Performance optimisation

Kubernetes

Multi-tenant infra

Hyperscaler experience

Quantisation/Distillation

SLA-driven infra

Leadership

Tools

vLLM

TensorRT-LLM

Triton Inference Server

SGLang

Job description

Fuse Energy seeks a founding engineer to define and build our inference serving stack, driving architecture decisions for high-throughput, low-latency workloads. You will own model-level optimisation strategies, including quantisation and speculative decoding, and collaborate with CUDA/GPU teams to integrate performance work.

The role reports directly to the CTO in a pioneering energy-AI platform, with equity and competitive compensation in a fast-growing startup environment.