Senior ML Engineer - Real-Time Inference & Scalable Systems

careers.bitkraft.vc - Jobboard; Germany (OH); On-site; USD 120,000 - 160,000; Full time

Job summary

Inworld is seeking an experienced ML Engineer in the United States. You will work on high-performance multimodal models and lead the optimization of performance in production systems. Candidates should have solid experience with C++, CUDA, Kubernetes, and a deep understanding of machine learning frameworks. A PhD in a related field is preferred. This role involves close collaboration with leadership teams and may include relocation support to the San Francisco Bay Area.

Qualifications

• Deep understanding of modern serving frameworks and techniques like vLLM or TRT-LLM.
• Hands-on experience with quantization, distillation, caching strategies, continuous batching.
• Proficiency in C++, CUDA, Rust, or optimized Python.
• Experience with Kubernetes and multi-GPU inference.

Responsibilities

• Develop high-performance models under real-time constraints.
• Collaborate with teams on implementing scalable ML solutions.
• Optimize model performance and ensure reliability in production.

Skills

C++

CUDA

Rust

Python

Kubernetes

Deep Learning

Performance Optimization

ML Systems

Education

PhD in Computer Science, Physics or Math

Job description

Inworld is seeking an experienced ML Engineer in the United States. You will work on high-performance multimodal models and lead the optimization of performance in production systems. Candidates should have solid experience with C++, CUDA, Kubernetes, and a deep understanding of machine learning frameworks. A PhD in a related field is preferred. This role involves close collaboration with leadership teams and may include relocation support to the San Francisco Bay Area.