about 4 hours ago
Responsibilities
- Design, build, and improve systems connecting AI capability development to production inference.
- Build and enhance model-serving pathways for low-latency, high-throughput inference workloads.
- Operate and optimize containerized workloads on Kubernetes/GCP with a focus on NVIDIA GPU utilization.
- Integrate model-serving frameworks and adapt them to internal deployment and observability requirements.
- Enable safe traffic management and release strategies for model-backed services.
- Develop tooling for benchmarking latency, throughput, and reliability under production traffic.
- Improve artifact lifecycle management for model and capability deployments.
- Enhance observability and debug capabilities for model-serving behavior in production.
- Contribute to strategies for compute efficiency and cost-performance tradeoffs.
Requirements
- 6+ years of professional software engineering experience in production engineering.
- Proficiency in Python, Go, or another backend-oriented language.
- Experience with high-throughput services, distributed systems, or ML infrastructure.
- Hands-on experience with containers, Kubernetes, and Linux environments.
- Strong operational judgment regarding reproducibility and system resilience.
- Ability to reason about performance bottlenecks across various system components.
- Collaboration skills to work with model developers and technical leadership.
Benefits
- Competitive salary and comprehensive benefits.
- Opportunities for growth and professional development.
- Access to cutting-edge AI tools and a robust training program.
- Inclusive office environment designed for collaboration.
- Recognition as a Great Place to Work, fostering a culture of value and empowerment.