LLM & Agentic AI Performance Engineer
Intel Corporation (company site, opens in a new tab)10+ yrsBengaluruOn-siteDirect career pageEst. 35–60 LPA
Posted 9h ago
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
Reach people at Intel Corporation
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 Intel Corporation you could write to:
- Recruiters & HR
- People in this function
- Work addresses
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 performance characterization and optimization of LLM and Agentic AI workloads across software and hardware stack including AI frameworks, inference runtimes, Linux, and hardware counters.
- Identify and resolve complex performance bottlenecks to deliver measurable improvements, translating findings into code contributions, framework optimizations, BKCs, and customer-ready solutions.
- Collaborate across teams and open-source communities to integrate performance improvements influencing current and future Intel AI platforms.
Minimum Requirements
- Bachelor's degree +10 years or Master's degree +8 years in CS, CE, EE, or related fields.
- Significant hands-on experience in performance engineering, systems optimization, or workload characterization on server-class platforms.
- Strong programming skills in Python and C++ or equivalent systems programming languages (C/Rust).
- Experience with Linux performance and system tools (e.g., affinity, huge pages, cgroups, eBPF, ftrace, perf).
Ideal Candidate Profile
- Expertise in server architecture including cache hierarchy, memory bandwidth, NUMA, and system-level performance behavior.
- Proven ability to analyze and optimize AI serving stacks such as vLLM, SGLang, or TGI and familiarity with LLM inference techniques like KV-cache management and quantization.
- Experience with hardware counter-level performance analysis tools such as VTune, EMON/PMU, perf, top-down analysis, or roofline modeling and contributions to open-source projects.