Multimodal AI Model Optimization Research Engineer

US Health Partners, LLC; United States; Remote; USD 180,000 - 260,000; Full time

Benefits offered by this job

Flexible work schedules

Unlimited PTO

Healthcare

Gear stipend

Job summary

Tavus is seeking an experienced Research Scientist/Engineer focused on model optimization to join our core AI team in a role that blends research with production deployment.

We value individuals who thrive in startup settings, can work independently, and are willing to take calculated risks. This position offers relocation support and a path to high-impact AI systems in a fast-paced environment.

Qualifications

• Strong experience in deep learning using PyTorch.
• Hands-on experience with model optimization and compression (distillation, pruning, quantization, mixed precision).
• Understanding of efficient architectures such as low-rank adapters.
• Strong inference performance knowledge and GPU/accelerator fundamentals.
• Strong Python coding skills and reliable research engineering practices.

Responsibilities

• Take cutting-edge research models and make them 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 across latency, cost, and quality.
• Partner closely with researchers and engineers to turn new ideas into deployable systems.

Skills

PyTorch

Model optimization

Compression

Knowledge distillation

Pruning/sparsification

Quantization

Mixed precision

Low-rank adapters

Inference performance

GPU fundamentals

Python coding

Cloud environments

Papers & reproducibility

Communication

Tools

TensorRT

ONNX Runtime

TVM

Triton

XLA

Job description

About Us

At Tavus, we're building the human layer of AI. Our mission is to make human-AI interaction as natural as face-to-face interaction, enabling the human touch where it has been previously unscalable.

We achieve this through pioneering research in multimodal AI for modeling human-to-human communication (language, audio, and video), as well as generating audio-visual avatar behavior. Our models power everything from text-to-video AI avatars to real-time conversational video experiences across industries like healthcare, recruiting, sales, and education.

By enabling AI to see, hear, and communicate with human-like authenticity, we're creating the foundation for the next generation of AI employees, assistants, and companions.

We are a Series B company backed by top investors, including Sequoia, Y Combinator, and Scale VC. Join us in driving the future of human-AI interaction.

The Role

We’re looking for an experienced Research Scientist/Engineer with a focus on model optimization to join our core AI team.

Our ideal partner-in-crime thrives in startup environments, is comfortable prioritizing independently, and is willing to take calculated risks. We’re moving fast and looking for people who can help pave the path.

Your Mission

• Take cutting-edge research models and make them 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 across latency, cost, and quality

• 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, including knowledge distillation, pruning/sparsification, quantization, and mixed precision

• Understanding of efficient architectures such as low-rank adapters

• Strong understanding of inference performance and GPU/accelerator fundamentals

• Strong Python coding skills and reliable research engineering practices

• Experience working with large models and datasets in cloud environments

• Ability to read ML papers, reproduce results, and adapt ideas

• Clear communication and collaboration skills

Preferred Experience

• Optimization of diffusion models, video/audio generative models, or large language models

• Experience with real-time or streaming systems (low-latency APIs, WebRTC, streaming TTS/video)

• Familiarity with TensorRT, ONNX Runtime, TVM, Triton, or XLA

• Experience writing custom Triton/CUDA kernels or low-level performance tuning

• Experience with experiment tracking, benchmarking, and profiling at scale

• Prior experience in research engineering or applied science roles

Location

This position is preferably hybrid in San Francisco, with relocation support offered. Remote candidates are also considered.

Benefits

When you join Tavus, you’re joining a family. We offer flexible work schedules, unlimited PTO, competitive healthcare and gear stipends, and a collaborative environment focused on learning and impact.

Culture & Diversity

We are not looking for cultural fits — we are looking for culture creators. Diversity drives our success, and we combine varied backgrounds, skills, and perspectives to build the best experiences for our clients..