Multimodal AI Model Optimization Research Engineer
TavusGenerative AI company
San Francisco, United StatesSenior
CRV
Scale Venture Partners
Sequoia Capital
Y Combinator
HubSpot Ventures
Flex Capital
Data & AI
About the role
TL;DR
Optimize multimodal AI models for speed, efficiency, and production readiness.
- •Tavus is building the human layer of AI, making human-AI interaction as natural as face-to-face.
- •This role focuses on optimizing cutting-edge multimodal AI models for speed and efficiency.
- •Key Responsibilities Make cutting-edge research models fast, efficient, and production-ready using sparsification, distillation, and quantization.
- •Own the optimization lifecycle for key models: define metrics, run experiments, and benchmark trade-offs.
- •Partner closely with researchers and engineers to turn new ideas into deployable systems.
- •Requirements Strong experience in deep learning using PyTorch.
- •Hands-on experience with model optimization and compression (knowledge distillation, pruning, quantization).
- •Understanding of efficient architectures and inference performance fundamentals.
- •Strong Python coding skills and reliable research engineering practices.
Required skills
PythonPyTorchLLMsComputer VisionNLPMLflowONNXJAX
Domain expertise
ai
Benefits & perks
Flexible work schedules, Unlimited PTO, Competitive healthcare, Gear stipends
Tech stack
PythonPyTorchTensorFlowscikit-learnKerasHugging FaceComputer VisionNLPLLMsONNXJAX
