Senior Real-Time Multimodal Model Engineer - AI Focus

About the Role

We're hiring a Senior Real-Time Multimodal Model Engineer to join our innovative team at Inworld AI. This Senior Real-Time Multimodal Model Engineer remote position offers an exciting opportunity to work with cutting-edge AI technologies and contribute to the development of best-in-class real-time multimodal models.

What You'll Do

• Optimize inference processes and implement modern serving frameworks like vLLM or TRT-LLM.
• Accelerate models using techniques such as quantization, distillation, and caching strategies.
• Develop high-performance systems leveraging C++, CUDA, Rust, or optimized Python.
• Scale distributed systems using Kubernetes and manage multi-GPU/multi-node inference.
• Engage in public work through open-source contributions and technical write-ups.
• Take ownership of models from research to production, ensuring reliability and performance.

Requirements

• PhD in Computer Science, Physics, Math, or equivalent practical experience.
• Strong background in machine learning and backend systems.
• Experience with high-performance computing and NVIDIA GPUs.
• Ability to work in ambiguous environments and tackle unclear problems.
• Proven track record of shipping stable, impactful engineering solutions.

Nice to Have

• Experience with open-source contributions.
• Familiarity with deep learning frameworks.
• Understanding of system programming and architecture.

What We Offer

• Competitive salary range of $270,000 - $500,000+ with bonuses and equity.
• Comprehensive relocation assistance to help you settle in.
• Flexible work environment with a focus on collaboration.
• Opportunities for professional growth and open-source contributions.
• A flat organizational structure that encourages innovation.