The role
- COMP
- $200K - $300K
- EQUITY
- Competitive Equity
- LOCATION
- Seattle
- WORKPLACE
- On-site
- EXPERIENCE
- 0 - 2 years
- VISA
- None, Visa transfers
- STACK
- Kubernetes, Terraform, Python, Rust, Go, Airflow, PyTorch
- INDUSTRY
- Software Development, AI
/roles — ROLE_76
Member of Technical Staff - Model Optimization and Inference (New Grad)
Face-to-face AI interaction that feels human
The company
Applied-AI lab building visual conversational AI — real-time, face-to-face interaction that feels human.
- STAGE
- growth-stage
- FUNDING
- $60M+ raised
- TEAM
- ~25 people
- FOUNDED
- 2024
JD — the work
About the role
For early-career engineers who want to squeeze every millisecond out of trained models: full-stack inference work — quantization, KV cache, kernels, batching — at a research lab building real-time conversational AI. BS/MS/PhD all welcome; systems intuition matters more than credentials.
What you'll do
- Contribute to inference optimization across LLM, audio, and diffusion models
- Implement KV-cache strategies for long-context conversation
- Work with and extend vLLM/SGLang/TensorRT-LLM-class frameworks
- Profile latency and throughput; eliminate bottlenecks
- Build internal profiling and test tooling
- Apply quantization techniques throughput-first
What they're looking for
- Finishing or recently finished BS/MS/PhD
- Framework exposure through coursework, research, internships, or open source — with opinions on where they fall short
- Appetite to go deep