MTS 2, AI Platform
eBay (company site, opens in a new tab)5+ yrsBengaluruOn-siteDirect career pageEst. 35–65 LPA
Posted on 16 Sept
Reach people at eBay
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at eBay you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own end-to-end production LLM inference pipeline including release engineering, capacity planning, cost optimization, and incident response.
- Optimize inference performance to reduce latency and increase throughput on real production traffic patterns across heterogeneous GPU fleets.
- Build benchmarking tools and improve reliability through monitoring, tracing, alerting, and incident management.
Minimum Requirements
- 5+ years of software development experience with production deployment and operation of LLM inference services.
- Strong coding skills in Python and either Go or Rust for systems-level implementation and debugging.
- Experience with ML frameworks and runtimes including PyTorch, vLLM, and related tools such as SGLang or TensorRT.
- Knowledge of GPU architecture and performance optimization; CUDA/kernel programming skills are a strong plus.
Ideal Candidate Profile
- Experienced in AI/ML systems programming focused on performance optimization for LLM inference workloads with demonstrated impact (e.g., doubling throughput, reducing latency).
- Skilled in root-cause analysis across models, runtimes, networking, and infrastructure to identify and resolve bottlenecks.
- Familiarity with applying autonomous AI coding agents to accelerate development and improve code quality in software delivery pipelines.