New Grad Staff Engineer — Real-Time Model Optimization

Nuance Labs; Seattle (WA); On-site; USD 200,000 - 300,000; Full time

Benefits offered by this job

Health Savings Account with $2,000 annual contributions

15 days of PTO plus public holidays

Lunch, drinks, and snacks provided daily

Job summary

Nuance Labs in Seattle is seeking a Member of Technical Staff focused on model optimization and inference. This role demands expertise in refining AI models for real-time interactions, requiring a strong foundation in ML systems and familiarity with frameworks like vLLM and SGLang.

Ideal candidates will have a BS, MS, or PhD-related field and exhibit a passion for optimizing AI performance. Benefits include a competitive salary and a supportive, innovative work environment.

Qualifications

• Excitement about real-time model optimization.
• Strong fundamentals in ML systems.
• Exposure to inference serving frameworks.

Responsibilities

• Contribute to end-to-end inference optimization.
• Implement KV cache strategies for long-context conversations.
• Profile and benchmark latency and throughput.

Skills

Python

PyTorch

LLM inference

KV caching

CUDA

Education

BS, MS, or PhD in CS, ML, or related field

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Nuance Labs in Seattle is seeking a Member of Technical Staff focused on model optimization and inference. This role demands expertise in refining AI models for real-time interactions, requiring a strong foundation in ML systems and familiarity with frameworks like vLLM and SGLang.

Ideal candidates will have a BS, MS, or PhD-related field and exhibit a passion for optimizing AI performance. Benefits include a competitive salary and a supportive, innovative work environment.