Applied ML Engineer

Job Summary

A company is looking for an Applied ML Engineer, Real Time Video Generation.

Key Responsibilities

• Productionize video generation models into scalable inference APIs
• Optimize models for performance, focusing on latency, cost, and memory tradeoffs
• Build and maintain real-time inference systems with low latency serving and streaming outputs

Required Qualifications

• 2+ years of experience in ML engineering with ownership of deployed systems
• Proficient in PyTorch and Python, with experience in both training and inference
• Hands-on experience with generative models, particularly for image and video
• Demonstrated ability to improve latency and cost through optimization techniques
• Experience with WebRTC and cloud environments, including Docker and Kubernetes