Founding AI Inference Engineer for Energy AI

Fuse Energy, LLC; Greater London; Hybrid; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Equity

Biannual bonus

Fully expensed tech

Private health insurance

Meal allowance

Job summary

Fuse Energy is building a fully integrated energy company that merges generation, hardware, grid, trading, AI, and distributed energy. We are seeking the founding engineer to own the inference serving layer, guiding performance, reliability, and deployment across a growing cluster.

You will define the serving strategy, design high-throughput workloads, and collaborate with CUDA/GPU teams to optimize throughput and cost per token while meeting ambitious uptime targets.

Qualifications

• 4+ years building or operating large-scale inference serving systems.
• Hands-on experience with inference serving frameworks and the techniques used to optimise them (batching, KV-cache management, quantisation, speculative decoding).
• Strong systems thinking across a large cluster.
• Ability to work with GPU/CUDA engineers to integrate performance work into a serving system.
• Track record of making high-stakes architecture calls and owning the outcome.
• Founding role; comfortable with ambiguity and shaping a new function.

Responsibilities

• Define Fuse's inference serving strategy and architecture from first principles.
• Design and build the serving stack: request routing, batching, scheduling and autoscaling for high-throughput, latency-sensitive inference workloads.
• Own model-level optimisation strategy for serving, applying quantisation, distillation and speculative decoding.
• Make the core software architecture calls on serving frameworks and orchestration (e.g. vLLM, TensorRT-LLM, SGLang, Triton Inference Server).
• Translate throughput, latency and uptime commitments into concrete technical specifications and capacity plans.
• Act as direct technical owner of inference performance and reliability.
• Collaborate with CUDA/GPU engineers to integrate custom kernels and hardware performance into the serving layer.
• Set the standards, tooling and benchmarks this function will run on as it grows.

Skills

Inference serving

Architecture

Batching

KV-cache management

Quantisation

Speculative decoding

System architecture

Autoscaling

GPU collaboration

Serving frameworks

Tools

Triton Inference Server

vLLM

TensorRT-LLM

SGLang

Kubernetes

Job description

Fuse Energy is building a fully integrated energy company that merges generation, hardware, grid, trading, AI, and distributed energy. We are seeking the founding engineer to own the inference serving layer, guiding performance, reliability, and deployment across a growing cluster.

You will define the serving strategy, design high-throughput workloads, and collaborate with CUDA/GPU teams to optimize throughput and cost per token while meeting ambitious uptime targets.