AI Inference Engineer

New

Fuse EnergyRenewable Energy AI

London, England, United Kingdom. United States. Dubai, Dubai, United Arab Emirates. United KingdomFull-TimeSenior

SalaryCompetitive salary and an equity sign-on bonus. Biannual bonus scheme.

Apply NowOpens the employer's application page

Job Details

4+ years of experience building or operating large-scale inference serving systems.
Deep, hands-on experience with inference serving frameworks.
Proficiency in optimization techniques such as batching, KV-cache management, quantization, and speculative decoding.
Strong systems thinking capabilities to reason about end-to-end request handling.
Experience working directly with GPU/CUDA engineers to integrate low-level performance work.
Proven track record of making high-stakes architecture decisions and owning outcomes.
Ability to operate effectively in an early-stage, unstructured environment.
Nice to have: Experience with Triton or custom ML inference/training frameworks.
Nice to have: Experience with autoscaling or capacity planning.
Nice to have: Familiarity with Kubernetes or Slurm for cluster orchestration.

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 techniques like quantisation, distillation, and speculative decoding.
Make core software architecture calls on serving frameworks and orchestration (e.g., vLLM, TensorRT-LLM, SGLang, Triton Inference Server).
Translate performance and uptime commitments into technical specifications and capacity plans.
Act as a direct technical owner of inference performance and reliability.
Partner with CUDA and GPU engineering teams to integrate custom hardware performance work into the serving layer.

View Full Description & ApplyYou'll be redirected to the employer's site