Cerebras Systems is hiring a Senior Software Engineer to advance its ML inference APIs, crucial for AI applications. This hands-on role emphasizes developing fast, reliable API solutions for the world’s largest AI chip.

In this versatile position, you will enhance existing infrastructure and design recent APIs that facilitate real-time AI applications. The ideal candidate will thrive in a collaborative environment and contribute to optimizing performance while ensuring API integrity and user satisfaction.

Key Responsibilities:



• Build and maintain ML inference APIs that support tool calling and multimodal inputs • Ensure a unified experience across diverse machine learning models • Collaborate on integrating library features with existing runtimes • Design robust testing and qualification measures for APIs • Optimize request handling and throughput for production systems

Requirements: • 5+ years in software engineering, with a focus on production APIs • Strong programming skills in Python, Go, and familiarity with C++ • Expertise in building reliable, performant APIs and distributed systems • Experience with cloud infrastructure and container orchestration • Excellent communication skills and ability to translate user needs into software solutions

Drive innovation at Cerebras by developing robust ML APIs that enhance AI capabilities and improve user interactions.

📌 Senior Software Engineer for ML Inference APIs (Toronto)
🏢 Cerebras
📍 Toronto