Founding AI Inference Engineer (AI)

Location: Remote; listed locations are London, England, United Kingdom and the United States

Company

hirify.global is an energy startup building an integrated energy company spanning renewable generation, batteries, grid infrastructure, real-time power trading, distributed energy, and AI-powered high-performance compute infrastructure.

What you will do

• Define the inference serving strategy and architecture from first principles.
• Design and build request routing, batching, scheduling, and autoscaling for high-throughput, latency-sensitive workloads.
• Own model-level optimization using quantization, distillation, speculative decoding, and related techniques.
• Make architecture decisions across serving frameworks and orchestration, including vLLM, TensorRT-LLM, SGLang, and Triton Inference Server.
• Translate throughput, latency, and uptime commitments into technical specifications and capacity plans.
• Own inference performance and reliability while integrating CUDA, GPU, custom kernel, and hardware work into the serving layer.

Requirements

• 4+ years of experience building or operating large-scale inference serving systems, or equivalent strong project or industry experience.
• Deep hands-on experience with inference serving frameworks, batching, KV-cache management, quantization, and speculative decoding.
• Strong systems thinking across the full path from incoming request to served response across a large cluster.
• Experience working directly with GPU and CUDA engineers on low-level performance integration.
• Experience making high-stakes architecture decisions and owning the outcomes.
• Comfort shaping a new function without an established playbook.

Nice to have

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

Culture & Benefits

• Work in a founding role reporting directly to the CTO and shape a new engineering function.
• Competitive salary with equity eligibility and a biannual bonus scheme.
• Fully expensed technology matched to role requirements.
• Private health insurance.
• Benefits vary by location; breakfast and dinner allowances are available to office-based employees.