Staff Software Engineer - Ai Traffic & Inference Infrastructure

Coupang Inc

Bengaluru, India
On-site
Distributed systems architecture
Kubernetes internals expertise
Go or python programming
The role involves designing the intelligent nervous system for Coupang's Cloud AI platform to ensure high availability and low latency for LLMs

Job Summary

  • The role involves designing the intelligent nervous system for Coupang's Cloud AI platform to ensure high availability and low latency for LLMs.
  • Candidates will own the end-to-end lifecycle of traffic management, including global load balancing and hardware-aware request routing across thousands of accelerators.
  • The team operates with a startup culture backed by the resources of a large global public company, emphasizing bold innovation and hands-on impact.

Matching Summary

The role involves designing the intelligent nervous system for Coupang's Cloud AI platform to ensure high availability and low latency for LLMs.

Skills & Requirements

Must-have

  • Distributed systems architecture
  • Kubernetes internals expertise
  • Go or Python programming
  • Load balancing algorithms
  • High-availability system maintenance

Nice-to-have

  • LLM infrastructure experience
  • GPU/TPU hardware scheduling
  • Hybrid-cloud deployment knowledge
  • Low-latency optimization techniques
  • Cross-functional technical leadership

Key Requirements

  • 8–12 years of software engineering experience
  • Bachelor's or Master's degree in Computer Science
  • Expert-level Kubernetes knowledge
  • Proven track record in mission-critical systems

Work Rights

Not specified

Tailored Resume

Cover Letter