Senior Remote LLM Inference Optimization Lead

Dragonfly Digital Management, LLC (Dragonfly Capital); United States; On-site; USD 140,000 - 210,000; Full time

Job summary

Dragonfly Digital Management, LLC (Dragonfly Capital) seeks a Senior Inference Optimization Engineer to work remotely on GPU infrastructure optimization, LLM inference performance, and cost efficiency for a privacy-first consumer AI portfolio.

The role focuses on optimizing GPU throughput, evaluating inference engines, and applying cutting-edge techniques such as continuous batching and cache management to scale high-volume workloads.

Qualifications

• 5+ years in performance optimization or HPC with GPU architecture experience.
• Hands-on experience with production LLM inference engines at high volume.
• Experience with LLM optimization techniques such as continuous batching and KV cache management.
• Proficiency in Python, Rust, or Go; C++/CUDA is a strong plus.

Responsibilities

• Optimize GPU infrastructure and improve throughput and cost per token for LLM inference workloads
• Build benchmarking harnesses to identify optimal inference engines and strategies for various workloads
• Evaluate and implement emerging inference optimization techniques and hardware solutions

Skills

Performance optimization

HPC

LLM inference

Continuous batching

KV cache management

Python

Rust

Go

C++/CUDA

Tools

Nsight Systems

PyTorch Profiler

Job description

Dragonfly Digital Management, LLC (Dragonfly Capital) seeks a Senior Inference Optimization Engineer to work remotely on GPU infrastructure optimization, LLM inference performance, and cost efficiency for a privacy-first consumer AI portfolio.

The role focuses on optimizing GPU throughput, evaluating inference engines, and applying cutting-edge techniques such as continuous batching and cache management to scale high-volume workloads.