Founding AI Inference Engineer

Fuse Energy; United States; On-site; USD 180,000 - 300,000; Full time

Benefits offered by this job

Competitive salary and equity

Biannual bonus

Fully expensed tech to match needs

Private health insurance

Breakfast and dinner allowance

Job summary

Fuse Energy is hiring a founding engineer to own the inference serving layer, delivering high-throughput, low-latency model serving from kernel to endpoint. You will define the serving stack, partner with CUDA/GPU engineers, and shape the future of our energy AI platform.

In this founding role you will drive architecture decisions, experiment with quantisation and distillation techniques, and establish standards as the function scales, with equity available. This is a globally remote opportunity.

Qualifications

• 4+ years building or operating large-scale inference serving systems.
• Hands-on experience with inference serving frameworks and optimization techniques.
• Strong systems thinking across a large cluster.
• Collaborate with GPU/CUDA engineers to integrate performance work.
• Proven track record of making architecture calls and owning outcomes.
• Founding role; ability to shape a new function.

Responsibilities

• Define inference serving strategy and architecture from first principles.
• Design and build the serving stack for high-throughput, low-latency workloads.
• Own model-level optimisation including quantisation and distillation.
• Make architecture calls on serving frameworks and orchestration.
• Translate throughput, latency and uptime into concrete specs and capacity plans.
• Act as direct technical owner of inference performance and reliability.
• Collaborate with CUDA/GPU teams to integrate custom kernels into serving.
• Set standards, tooling and benchmarks as the function grows.

Skills

Inference serving

GPU/CUDA

Distributed systems

System design

Kubernetes/Slurm

LLMs

Tools

TensorRT

vLLM

Triton

SGLang

Job description

Fuse Energy is hiring a founding engineer to own the inference serving layer, delivering high-throughput, low-latency model serving from kernel to endpoint. You will define the serving stack, partner with CUDA/GPU engineers, and shape the future of our energy AI platform.

In this founding role you will drive architecture decisions, experiment with quantisation and distillation techniques, and establish standards as the function scales, with equity available. This is a globally remote opportunity.