Join As LLM & Agentic AI Performance Engineer At Intel | Apply Now
Job Overview:
| Company | Intel |
|---|---|
| Job Role | LLM & Agentic AI Performance Engineer |
| Job ID | JR0287957 |
| Work Location | Bangalore |
| Work Mode | Hybrid |
| Job Type | Full-Time |
| Experience | 8+ to 10+ years |
| Qualification | B.E. / M.Tech |
| Salary | Not disclosed |
| Careers Page | www.intel.com |
Skills: Python C++ C Rust Linux LLM Inference vLLM SGLang TGI VTune Performance Engineering
Optimize cutting-edge LLM and Agentic AI workloads at Intel Bangalore
Intel is hiring an LLM & Agentic AI Performance Engineer in Bangalore for their Data Center AI organization. This role involves end-to-end performance characterization and optimization across AI frameworks, runtimes, and server hardware.
Who Can Apply?
- Candidates with B.E. and 10+ years or M.Tech and 8+ years of experience in Computer Science, Computer Engineering, Electrical Engineering, or related fields.
- Professionals with hands-on experience in performance engineering, systems optimization, or workload characterization on server-class platforms.
- Engineers with strong programming skills in Python and C++, or systems programming in C/Rust.
- Applicants with a strong understanding of server architecture including cache hierarchy, memory bandwidth, NUMA, and interconnects.
- Individuals with hands-on experience using Linux performance and system technologies such as affinity, huge pages, cgroups, eBPF, ftrace, and perf.
About Intel:
Intel Corporation is a global technology leader focused on creating world-changing technology that enables global progress and enriches lives. The company drives innovation in computing, data storage, and artificial intelligence solutions from the cloud to the edge.
What You Will Do as LLM & Agentic AI Performance Engineer
- Performance Characterization: Characterize and optimize LLM and Agentic AI workloads across the complete software and hardware stack.
- Bottleneck Identification: Identify performance bottlenecks across AI frameworks, inference runtimes, operating systems, memory, compute, and platform architecture.
- Framework Optimization: Design and develop hardware-aware and hardware-agnostic optimizations for AI frameworks and runtimes, focusing on KV-cache, attention, and quantization.
- Serving Stack Work: Work hands-on with AI serving stacks such as vLLM, SGLang, TGI, or equivalent technologies.
- System Debugging: Analyze host and accelerator performance using tools like VTune, EMON/PMU, perf, and debug complex performance issues spanning Python, native code, and Linux.
Skills Required:
Programming Languages. Strong programming capability in Python, C++, C, or Rust for systems and AI workload optimization.
AI Frameworks & Serving. Experience with LLM serving stacks and inference optimization techniques such as KV-cache, quantization, and continuous batching.
Systems & Profiling Tools. Proficiency with Linux performance utilities, hardware counters, VTune, and roofline modeling.
How to Prepare
Our tips, based only on what the listing asks for:
- Brush up on server architecture concepts such as NUMA, cache behavior, memory bandwidth, and silicon-level performance counters.
- Strengthen your understanding of LLM inference mechanics like KV-cache management, paged attention, continuous batching, and quantization formats like INT8, INT4, or FP8.
- Practice profiling and debugging code using tools such as VTune, EMON/PMU, perf, and roofline modeling.
- Be prepared to discuss your experience working with AI serving stacks like vLLM, SGLang, TGI, or OpenVINO during technical rounds.
What the Listing Does Not Mention
- No specific salary or CTC package is mentioned in the job posting.
- No last date or application deadline is provided.
- No exact interview dates or selection process stages are stated.
How to Apply: Intel
- Visit the official Intel careers page using the apply link below.
- Review the detailed job description and minimum qualifications for job ID JR0287957.
- Submit your resume and complete the online application process.
Build the future of AI performance at Intel by connecting silicon capabilities with real-world AI software.
Important Links:
| Events | Links |
|---|---|
| Apply Now | Click Here |
| Official Careers Page | Click Here |
Frequently Asked Questions:
What qualification is required?
Required qualification: B.E. / M.Tech. See the eligibility section above for details.
Is this a fresher job?
No, this role requires significant experience (8+ years for M.Tech or 10+ years for B.E.).
Where is the job located?
The position is based in Bangalore, India.
What is the work mode?
This role is eligible for Intel's hybrid work model.
Is coding required?
Yes, strong programming skills in Python and C++, or C/Rust, are required.
Stay safe: Intel does not charge any fee to apply or to give an interview. If anyone asks you for money for a job, a referral or an offer letter, it is a scam.
Source: the official Intel careers listing for this role.
Related Jobs You May Like
- Join As Diagnostics Firmware Engineer At Intel | Apply Now
- Join As Chassis IP Design Engineer At Intel | Apply Now
- Join As AI Software Solutions Engineer At Intel | Apply Now
- Join As Microarchitecture and Design Engineer – AI SoC At Intel | Apply Now
Disclaimer: This job post is for information only. All applications and questions should go to Intel through the official process.
About us:
CareerFinder.co.in: At CareerFinder.co.in, we are committed to connecting individuals with top-notch job opportunities seamlessly. Explore endless possibilities for your career growth and success with us.