Inference Engineer at Nuance Labs

Department: Research

Compensation

$200,000 – $300,000/yr

Location: Seattle, Washington
Type: Full-time
Level: entry
Posted: Jun 11, 2026

Description

Nuance Labs is hiring an early-career Inference Engineer to optimize end-to-end inference for its real-time, full-duplex multimodal AI avatar system. The role focuses on LLM, audio, and diffusion-model inference; KV cache and memory-efficient attention strategies; vLLM, SGLang, and TensorRT-LLM serving; latency and throughput profiling; quantization; kernel and batching optimizations; and internal optimization tooling. Candidates should have a BS, MS, or PhD in a relevant field, strong Python and PyTorch skills, and exposure to inference frameworks or ML systems. The position is in-person in Seattle five days per week, offers $200,000–$300,000 base salary plus equity, and provides visa sponsorship and health benefits.

Required Skills

LLM inference
KV cache
vLLM
SGLang
TensorRT-LLM
Python
PyTorch
CUDA
Triton
Quantization
Diffusion inference

Additional Information

Minimum Education: Bachelor's, master's, or PhD in computer science, machine learning, or a related field, completed or in the final stretch
Required Previous Experiences: Foundational experience in LLM inference or ML systems through coursework, research, internships, or open-source
Exposure to inference serving frameworks at a research or hobby level
Preferred Qualifications: Familiarity with CUDA or Triton
Internship or research experience with LLM inference, ML systems, or model serving
Contributions to open-source inference frameworks
CUDA or Triton kernel work
Publications or research projects in MLSys, model compression, or inference optimization
Familiarity with multimodal or streaming inference architectures
Experience with hard latency SLAs in real-time systems