Transform AI infrastructure as a Performance Systems Engineer at Baseten. You'll be integral in building systems that gauge and enhance performance metrics for AI models, working in a fully remote capacity.As a part of our expansion, Baseten is looking for early-career engineers skilled in high-performance computing and Large Language Model engineering. You will build and automate tools for model evaluation and stress testing, ensuring that our systems are set for success. Your deep dive into performance profiling will be a game-changer in maximizing efficiencies.Key Responsibilities:
Automate and execute LLM quality benchmarks for various workloads
Implement tests validating GPU infrastructure’s performance
Maintain and optimize GPU-enabled settings for development




Build tools for calculating model performance and configurations
Develop monitoring systems to track performance metrics in real-timeRequirements:
Enthusiastic about hardware and AI system optimization
Aptitude for automation and script creation for testing tasks
Desire to understand math related to AI models comprehensively
Proficient in Python, with a basic grasp of C++ preferred
Keen interest in exploring optimization strategies for modelsLeverage your skills in performance engineering and GPU systems with Baseten to shape the landscape of AI technology.#J-18808-Ljbffr

📌 Performance Systems Engineer At Baseten Montreal (Canada)
🏢 Baseten
📍 Canada