Multimodal AI Optimization Research Engineer

Tavus; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Health coverage

Unlimited PTO

Flexible hours

Remote-friendly

Learning stipend

Company retreats

Gear stipend

Job summary

Tavus is seeking an experienced Research Scientist/Engineer focused on model optimization to join our core AI team. You will take cutting-edge models and accelerate them for production using sparsification, distillation, and quantization.

You will own the optimization lifecycle, define metrics, run experiments, and benchmark latency, cost, and quality. Collaboration with researchers and engineers will turn ideas into deployable systems at Tavus.

Qualifications

• Thrives in startup environments and takes calculated risks.
• Ability to read ML papers, reproduce results, and adapt ideas.
• Strong Python coding skills and reliable research engineering practices.
• Experience with large models and datasets in cloud environments.
• Hands-on experience with model optimization and compression: distillation, pruning, quantization, mixed precision.
• Understanding of efficient architectures such as low-rank adapters.
• Experience with deep learning using PyTorch.

Responsibilities

• Own the optimization lifecycle for key models: define metrics, run experiments, and benchmark trade-offs across latency, cost, and quality.
• Partner closely with researchers and engineers to turn new ideas into deployable systems.
• Take cutting-edge research models and make them fast, efficient, and production-ready using sparsification, distillation, and quantization.
• We’re looking for someone who can move fast and pave the path in a startup.

Skills

Python

PyTorch

Deep learning

Inference optimization

Experiment tracking

Communication

Cloud environments

Diffusion models

Tools

TensorRT

ONNX Runtime

TVM

Triton

CUDA

Job description

Tavus is seeking an experienced Research Scientist/Engineer focused on model optimization to join our core AI team. You will take cutting-edge models and accelerate them for production using sparsification, distillation, and quantization.

You will own the optimization lifecycle, define metrics, run experiments, and benchmark latency, cost, and quality. Collaboration with researchers and engineers will turn ideas into deployable systems at Tavus.