Profile cover
O

AI Inference Cost Optimization Lead

Owen Goldberg

Full-time · Job · New_York

About the role

Our LLM serving infrastructure processes 180 million inference requests per day. At current pricing, that's $2.4M per month in compute costs — and our clients expect us to keep margins while token prices race to the bottom. Every 10% cost reduction is $240K monthly straight to the bottom line. This role is pure optimization engineering. You'll implement speculative decoding that cuts latency by 40%, design batching strategies that maximize GPU utilization during variable load, build quantization pipelines that maintain quality at INT4 precision, and architect the caching layer that eliminates redundant computation across similar prompts. Each technique has trade-offs; your job is finding the combination that minimizes cost per token while meeting our quality and latency SLAs. You'll lead a pod of three engineers and report to the CTO. This is the highest-leverage technical role in the company — your decisions directly determine whether we're profitable or not.

Responsibilities

  • Lead inference cost optimization across the LLM serving infrastructure
  • Implement speculative decoding, dynamic batching, and KV-cache optimization
  • Build quantization pipelines maintaining quality at reduced precision
  • Design prompt caching strategies to eliminate redundant computation
  • Set cost-per-token targets and track optimization progress
  • Lead a pod of three engineers focused on serving efficiency

Requirements

  • 7+ years in ML infrastructure with LLM serving optimization experience
  • Deep expertise in GPU programming, CUDA, and inference optimization
  • Experience with quantization, distillation, and model compression
  • Strong understanding of transformer architecture internals
  • Track record of measurable cost reduction in production ML systems

Benefits

  • Fully remote — US time zones
  • $200K+ base plus significant equity
  • Health, dental, vision, and life insurance
  • $6,000 annual learning budget
  • Direct P&L impact and board visibility

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

MLOps & AI Infrastructure AI & Machine Learning Engineers

Skills

python pytorch docker kubernetes aws

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior Product Security Engineer

RemoteAI company

Full-time Senior

AI Resident UK/EMEA

RemoteAI company

Full-time

Devops Engineer, US

RemoteAI company

Full-time

Infrastructure Engineer

RemoteAI company

Full-time

Senior AI Researcher- Pre-training (f/m/d)

RemoteAI company

Full-time Senior

Senior AI R&D Engineer – Model Training (f/m/d)

RemoteAI company

Full-time Senior

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$200k+ / year

AI Expertise

MLOps & AI Infrastructure AI & Machine Learning Engineers

Skills

python pytorch docker kubernetes aws gcp

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile
Create free account & apply Log in

Interested in this role? Create your free profile to apply.

Apply — create free profile