AI System Performance Architect

Intel Technology India Pvt Ltd; Bengaluru; Hybride; INR 2 500 000 - 5 000 000; Plein temps

Résumé du poste

Intel Technology India Pvt Ltd in Bengaluru seeks an AI System Performance Architect to own end-to-end performance modelling of AI training and inference systems, focusing on parallelism, interconnect behavior, and multi-GPU simulation. You will translate SLA targets into architectural guidance for future Intel AI platforms.

The role requires strong Python skills and deep knowledge of LLM training mechanics, including batching policies and KV cache, with experience in distributed parallelism and

Qualifications

• Proficiency in Python for modular analytical models and simulation frameworks.
• Strong understanding of AI training/inference systems and performance modelling.
• Experience with distributed parallelism and multi-GPU interconnects (NVLink/PCIe/CXL).
• Background in LLM inference training mechanisms and batching policies.

Responsabilités

• Own end-to-end AI training/inference system understanding and build analytical models and multi-GPU simulations.
• Model inferencing strategies across frameworks and coverage of batching and KV cache.
• Analyze data, pipelines, tensors, and expert parallelism and their communication patterns.
• Drive SLA-target studies and deliver optimization recommendations for architecture.

Connaissances

Python

Distributed parallelism

Multi-GPU simulation

MPI/collective communication

LLM inference

Formation

Bachelor's/Master's/PhD in Electrical Engineering, Computer Engineering, Computer Science

Outils

VTune

Nsight

Description du poste

AI System Performance Architect

About the Role We are looking for a talented and motivated AI System Performance Architect. The role owns the end-to-end understanding of AI training and inference systems, sitting where serving strategy, parallelism, collective communication, and interconnect behavior come together. Through analytical modelling and multi-GPU simulation, the candidate translates SLA and deployment targets into concrete architectural guidance for Intel's future AI platforms. Strong analytical skills and the ability to present performance findings and configuration recommendations to engineering and leadership teams are essential.

Key Responsibilities

• Own end-to-end understanding of the AI training/inference system and build analytical models and multi-GPU simulation - including MPI/collective communication (allgather, allreduce, all-to-all) and interconnect contention - to project performance, expose architectural bottlenecks, and recommend optimal Intel system configurations.


• Model inferencing strategies - static batching, continuous batching, disaggregated serving, and chunked prefill - across frameworks such as vLLM and SGLang, covering agentic inferencing, prefix caching, and multi-turn flows.


• Cover data, pipeline, tensor, and expert parallelism and their communication patterns.


• Drive studies against SLA targets - batch size, TTFT, TPOT, ISL/OSL, and TPS.


• Analyse regression run traces and find patterns in utilization counters across SLA operating points to identify architectural bottlenecks.


• Perform what-if analysis by sweeping core count, memory/cache capacity and bandwidth, fabric bandwidth, GPU interconnect, and deployment options; deliver optimization and optimal architecture recommendations.


• Scout whitepapers, blogs, and conferences; keep self and team updated on AI innovations applicable to Intel's end-to-end system.

Required Qualifications

• Bachelor's, master's or PhD in Electrical Engineering, Computer Engineering, Computer Science, or a related field.


• Bachelors with 8+ yrs, master’s with 6+ years and Ph.D. with 3+ years of experience in system performance modelling, AI workload analysis, or hardware architecture.


• Strong proficiency in Python, with the ability to build modular, maintainable analytical models and simulation frameworks.


• Solid understanding of LLM inference and training mechanics: prefill vs. decode, KV cache, batching policies, and quantization.


• Working knowledge of distributed parallelism strategies and their communication patterns.


• Familiarity with multi-GPU interconnect architectures (NVLink, PCIe, CXL, or equivalent).


• Understanding of SoC and platform fundamentals: core count scaling, cache/memory capacity and bandwidth, and fabric behavior.

Good-to-Have Skills

• Experience building discrete-event simulators for multi-node or multi-accelerator systems.


• Familiarity with performance profiling tools (e.g., Intel VTune, NVIDIA Nsight, or similar).


• Prior experience in a semiconductor or hardware company working on AI accelerator or platform products.

Join Intel and be part of a team that is shaping the future of data-driven innovation.

Seize the opportunity to make a meaningful impact through your expertise and creativity.

Job Type: Experienced Hire Shift: Shift 1 (India) Primary Location: India, Bangalore Additional Locations:

Posting Statement: All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation or any other characteristic protected by local law, regulation, or ordinance.

Position of Trust N/A

Work Model for this Role This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site.

Job posting details (such as work model, location or time type) are subject to change. ADDITIONAL INFORMATION: Intel is committed to Responsible Business Alliance (RBA) compliance and ethical hiring practices.

We do not charge any fees during our hiring process. Candidates should never be required to pay recruitment fees, medical examination fees, or any other charges as a condition of employment. If you are asked to pay any fees during our hiring process, please report this immediately to your recruiter.