AI/ML Inference Engineer

About Krea: Krea is an innovative AI startup specializing in browser-based creative tools powered by advanced AI systems. We focus on delivering unparalleled personalization, controllability, and aesthetic capabilities through state-of-the-art AI models. Our clients include industry giants like Pixar, Shopify, Fox News, and Amazon Studios. We’re backed by prominent investors including a cofounder of Meta/Facebook AI Research and a founding member of OpenAI.

About the Role: As an AI/ML Inference Engineer at Krea, you’ll play a critical role in deploying and optimizing cutting-edge AI models for our creative tools. You’ll work on scaling inference across our distributed systems, ensuring our AI capabilities deliver exceptional performance and reliability.

Key Responsibilities:

• Design, develop, and deploy scalable AI inference systems
• Optimize ML models for real-time performance in browser environments
• Collaborate with research teams to translate cutting-edge models into production-ready solutions
• Implement monitoring and maintenance for AI services
• Troubleshoot and resolve technical issues in AI systems

Required Skills:

• Proficiency in Python, C++, CUDA, and PyTorch
• Experience with model optimization and quantization techniques
• Understanding of distributed systems and GPU acceleration
• Strong background in machine learning inference deployment
• Excellent problem-solving skills with a focus on system performance
• Experience working with cloud platforms (AWS, GCP, Azure)

Ideal Candidate:

• 5+ years of experience in AI/ML engineering
• Proven track record in deploying ML models at scale
• Passion for creative applications of AI
• Ability to work in fast-paced startup environment
• Strong communication skills for cross-functional collaboration
• Experience with containerization and orchestration tools