Infra Software Engineer III — RankEmbed, Low-Latency

Google Inc.; Zürich; On-site; CHF 120,000 - 180,000; Full time

Job summary

Google Inc. is seeking a Software Engineer III for the RankEmbed infrastructure to help scale and optimize serving and indexing components.

You will work on high‑throughput systems, collaborate with SREs, and contribute to deployment strategies across teams to meet demanding latency targets. The role emphasizes designing robust rollout plans, analyzing bottlenecks, and improving ML infrastructure alongside other engineers in a fast-paced environment.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 2 years of experience with software development with C++ or 1 year with an advanced degree in an industry setting.
• 2 years of experience with developing large-scale infrastructure, distributed systems or networks, or experience with compute technologies, storage or hardware architecture.

Responsibilities

• Work on RankEmbed’s serving and indexing infrastructure that is currently serving millions of QPS at a low latency -- identify bottlenecks and deploy robust solutions.
• Design, implement and execute a robust rollout plan for the multiple components involved in RankEmbed’s model refreshes.
• Collaborate with SREs and Core on designing and implementing best practices to improve the existing ML infrastructure.
• Work with clients inside and outside of Search to understand their requirements and define their deployment strategy.
• Evaluate and analyze the performance of the various infrastructure components to identify their limitations and avenues for improvement.

Skills

C++

Distributed systems

Large-scale infrastructure

Education

Bachelor's degree or equivalent practical experience

Master's degree or PhD in CS or related field

Tools

Flume

Pod

Scaffolding

Job description

Google Inc. is seeking a Software Engineer III for the RankEmbed infrastructure to help scale and optimize serving and indexing components.

You will work on high‑throughput systems, collaborate with SREs, and contribute to deployment strategies across teams to meet demanding latency targets. The role emphasizes designing robust rollout plans, analyzing bottlenecks, and improving ML infrastructure alongside other engineers in a fast-paced environment.