F

Fuse Energy UK

Vertically integrated energy: generation, trading, retail

AI Inference Engineer

Applied Machine LearningConfirmed live in the last 24 hours
Full-timeRemote in UK

About the Job

Requirements

  • At least 4 years building or operating large-scale inference serving systems, or equivalent strong project or industry experience.
  • Hands-on experience with inference serving frameworks and optimization techniques, including batching, KV-cache management, quantization, and speculative decoding.
  • Ability to reason across the full request-to-response path in a large cluster.
  • Ability to work directly with GPU/CUDA engineers to integrate low-level performance work into a serving system.
  • Track record of making high-stakes architecture decisions and owning their outcomes.
  • Comfort operating without an established playbook in a founding role shaping a new function.

Responsibilities

  • Define the inference serving strategy and architecture from first principles.
  • Design and build the serving stack, including request routing, batching, scheduling, and autoscaling for high-throughput, latency-sensitive inference workloads.
  • Own the model-level optimization strategy for serving, selecting and applying quantization, distillation, speculative decoding, and similar techniques to improve throughput and cost per token, in partnership with CUDA/GPU engineers.
  • Make core software architecture decisions on serving frameworks and orchestration, such as vLLM, TensorRT-LLM, SGLang, and Triton Inference Server or equivalents.
  • Translate throughput, latency, and uptime commitments into technical specifications and serving capacity plans.
  • Own inference performance and reliability as the direct technical owner.
  • Work with CUDA and GPU engineering teams to integrate custom kernels and hardware performance work into the serving layer.
  • Set the standards, tooling, and benchmarks for the function as it grows.

Desired Qualifications

  • Experience with Triton or custom machine-learning inference or training frameworks.
  • Experience with autoscaling or capacity planning for large-scale inference.
  • Experience with multi-tenant serving or SLA-driven infrastructure.
  • Background at a hyperscaler, frontier AI lab, or large-scale distributed inference system.
  • Experience with Kubernetes or Slurm.
  • Interest in energy markets, grid systems, or sustainability-focused compute.

About the Company

Fuse Energy UK

Vertically integrated energy: generation, trading, retail

Fuse Energy UK is a London-based energy company that handles renewable generation, trading, and retail supply for households and businesses in a single chain. It owns and operates solar and wind farms, trades electricity to balance supply and price, and sells energy directly to customers, reinvesting profits into new renewable projects. Its edge comes from being vertically integrated across generation, trading, and retail, with strong backing from investors and a leadership team formerly at Revolut. Its goal is to grow its UK customer base and expand into Ireland, Spain, and the US while scaling up renewable capacity.

Company size
201-500
Company stage
Series B
Total funding
$200M
Headquarters
London, United Kingdom
Founded
2022

Recently Posted Jobs

Explore more opportunities at Fuse Energy UK

See more jobs