Founding AI Inference Engineer – Scale & Serving Expert

Fuse Energy; Greater London; On-site; GBP 150,000 - 210,000; Full time

Benefits offered by this job

Equity sign-on bonus

Biannual bonus

Fully expensed tech

Breakfast and dinner allowance

Job summary

Fuse Energy is seeking a founding AI Inference Engineer to define and build how we serve AI workloads at scale, reporting to the CTO. You’ll own the layer above CUDA/GPU work, shaping inference delivery, throughput, and reliability as we scale data-centre compute for energy applications.

With 4+ years in large-scale inference systems, you’ll collaborate with GPU engineers on model-level optimisations and architecture decisions, driving high-impact solutions across the platform.

Qualifications

• 4+ years of experience building or operating large-scale inference serving systems.
• Strong understanding of inference serving frameworks and optimisation techniques (batching, KV-cache management, quantisation, speculative decoding).
• Ability to reason about full request-to-response path across a large cluster.
• Track record of making high-stakes architecture calls and owning outcomes.

Responsibilities

• Define inference serving strategy and architecture from first principles.
• Design and build the serving stack: routing, batching, scheduling, autoscaling for high-throughput, low-latency workloads.
• Own model-level optimisation strategy to improve throughput and cost per token, in collaboration with CUDA/GPU engineers.
• Make core architectural calls on serving frameworks and orchestration (e.g., vLLM, TensorRT-LLM, SGLang, Triton).
• Translate throughput, latency, and uptime commitments into concrete specifications and capacity plans.
• Act as a direct technical owner of inference performance and reliability.
• Collaborate with CUDA and GPU teams to integrate performance work into the serving layer.
• Set standards, tooling, and benchmarks for this function as it grows.

Skills

Inference serving

System architecture

GPU/CUDA integration

Performance optimisation

Founding role experience

Tools

Triton Inference Server

vLLM

TensorRT-LLM

SGLang

Job description

Fuse Energy is seeking a founding AI Inference Engineer to define and build how we serve AI workloads at scale, reporting to the CTO. You’ll own the layer above CUDA/GPU work, shaping inference delivery, throughput, and reliability as we scale data-centre compute for energy applications.

With 4+ years in large-scale inference systems, you’ll collaborate with GPU engineers on model-level optimisations and architecture decisions, driving high-impact solutions across the platform.