Staff Software Engineer role focused on Vector Search Serving infrastructure for Google Cloud's Vertex AI platform, requiring experience with large-scale distributed systems and GenAI concepts.

Software Engineer III role focused on developing GenAI and Vertex-based development tools, including server and middleware code that interacts with LLMs. The role involves integrating next-generation LLMs with a focus on performance and deployment constraints, working closely with AI researchers and product managers.

Technical Lead for Vector Search Serving infrastructure within Google Cloud's Vertex AI platform, focusing on managing massive datasets and query volumes with low latency. The role involves technical leadership, architecture, code reviews, and mentoring engineers, with a requirement for experience in GenAI techniques.

Seeking an Engineering Manager with an infrastructure technical background to lead a team focused on optimizing planet-scale data processing infrastructure. This platform powers foundational AI/ML features and next-generation AI initiatives, with a focus on advancing scheduleability and auto-tuning for ML pipelines and standard data workloads. The role involves leading research into AI-driven optimization strategies and collaborating with teams working on frontier AI models.

Senior Software Engineer focused on optimizing AI/ML infrastructure performance across the technical stack, from networking and data storage to ML models, to provide AI developers with a high-performance experience on Google's AI infrastructure. Responsibilities include designing and implementing solutions, optimizing performance, profiling, debugging, and developing tools for AI/ML infrastructure.

Software Engineer role focused on implementing and designing Search features, leveraging advanced GenAI capabilities and LLM concepts, with a focus on Kubernetes-based infrastructure for scalability and performance.

Staff Software Engineer role focused on designing and leading feature development for the GKE Agent Gateway, enhancing capabilities for AI/ML workloads and contributing to the Kubernetes open-source project. The role involves collaboration with Load Balancing teams, ensuring optimal routing, load balancing, and autoscaling for inference serving, and improving observability, testability, and reliability of the Inference Gateway.

Software Engineer role focused on performance, reliability, and observability tools for Google Cloud control plane systems. The role involves analyzing VM performance, developing performance models, designing benchmarks, and exploring the use of machine learning for anomaly detection. While the core is engineering and performance analysis, there's an exploration component involving ML for anomaly detection.