Principal Software Engineer
Seeking a Principal Software Engineer to design and implement large-scale, high-performance distributed systems for AI model serving. This role involves optimizing inference performance, managing complex infrastructure, and ensuring the reliability and scalability of AI services.
What you'd actually do
- Design and implement large-scale, high-performance distributed systems for AI model serving.
- Optimize inference performance, latency, and throughput for various AI models.
- Develop and maintain robust infrastructure for deploying and managing AI services.
- Collaborate with AI researchers and engineers to integrate new models and techniques.
- Ensure the reliability, scalability, and security of AI serving platforms.
Skills
Required
- Deep expertise in distributed systems design and implementation
- Strong experience with high-performance computing and optimization techniques
- Proficiency in C++, Python, or similar programming languages
- Experience with AI model serving frameworks (e.g., TensorFlow Serving, TorchServe, Triton)
- Understanding of GPU computing and optimization
- Experience with cloud platforms (Azure, AWS, GCP)
Nice to have
- Experience with Kubernetes and containerization technologies
- Familiarity with AI/ML concepts and workflows
- Experience with performance profiling and debugging tools
What the JD emphasized
- large-scale
- high-performance
- distributed systems
- AI model serving
- inference performance
Other signals
- Large-scale distributed systems
- High-performance computing
- AI model serving