What sets this team apart is breadth of ownership: engineers here aren't limited to validating a single switch chip — they work across the full breadth of Marvell's AI platform portfolio, from Teralynx network fabrics to integrated optical platforms like co-packaged optics (CPO) and near-packaged optics (NPO), as well as emerging memory fabric products such as CXL and photonic fabric memory appliances. This cross-domain ownership — networking, optics, and memory, together — is work that's often siloed across separate teams elsewhere, and the results feed directly into customer proof points and executive reviews.
What You Can Expect
Drive end-to-end performance optimization across AI serving and training stacks using leading models and customer-relevant configurations.
Identify bottlenecks across the full data path, from application request flow through compute, memory, communication layers, GPU kernels, network transport, and data/storage pipelines.
Develop and execute benchmark methodologies that are reproducible, technically credible, and relevant to customer use cases.
Profile serving-stack internals — quantization, scheduling, KV-cache management, and disaggregated prefill/decode — to identify concrete optimization targets.
Analyze results and develop performance narratives that guide kernel, runtime, communication, and system-level optimizations.
Work closely with NRE / SRE and network or fabric architects to close competitive gaps through targeted tuning.
Create performance summaries, visuals, and benchmark artifacts for customer presentations, executive reviews, and trade-show demonstrations.
What We're Looking For
Required Qualifications
Experience with AI serving frameworks such as vLLM, SGLang, TensorRT-LLM, or similar platforms.
Strong background in RCCL/NCCL, RDMA, communication-compute overlap, and performance profiling.
Hands-on experience with any GPU profiling tools (e.g., Nsight Systems/Compute, PyTorch Profiler, or ROCm Compute Profiler) to localize bottlenecks at the kernel level.
Demonstrated ability to diagnose end-to-end bottlenecks across application, framework, runtime, and infrastructure layers.
Working knowledge of at least one distributed training framework (PyTorch DDP/FSDP, DeepSpeed, or Megatron-LM), given the role's scope spans both training and inference stacks.
Strong Python and Linux skills; Go experience is a plus.
Comfortable working in containerized environments (Docker; Kubernetes a plus) to ensure benchmark reproducibility.
Ability to translate deep technical analysis into clear recommendations and concise performance narratives.
Preferred Qualifications
Experience benchmarking distributed large-model inference and training systems.
Familiarity with GPU kernel analysis, system tracing, and workload-specific optimization.
Familiarity with serving-stack internals such as continuous batching, paged KV-cache attention, and quantization techniques (e.g., GPTQ, SmoothQuant).
Exposure to customer proofs of concept, competitive benchmarking, or externally consumed performance reporting.
Education
Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related field; a PhD is a plus.
- Expected Base Pay Range (USD)
- 186,900 - 275,000, $ per annum
The successful candidate’s starting base pay will be determined based on job-related skills, experience, qualifications, work location and market conditions. The expected base pay range for this role may be modified based on market conditions.

This role is eligible to participate in Marvell's bonus and equity plans, including a new hire equity grant and annual equity refreshers, ensuring you are rewarded for your contributions and remain invested in the company's long-term success.
 Additional Compensation and Benefit Elements Marvell is committed to providing exceptional, comprehensive benefits that support our employees at every stage - from internship to retirement and through life’s most important moments. Our offerings are built around four key pillars: financial well-being, family support, mental and physical health, and recognition. Highlights include an employee stock purchase plan with a 2-year look back, family support programs to help balance work and home life, robust mental health resources to prioritize emotional well-being, and a recognition and service awards to celebrate contributions and milestones. We look forward to sharing more with you during the interview process.
All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, sexual orientation, gender identity, disability or protected veteran status.
Any applicant who requires a reasonable accommodation during the selection process should contact Marvell HR Helpdesk at TAOps@marvell.com.
Interview Integrity
To support fair and authentic hiring practices, candidates are not permitted to use AI tools (such as transcription apps, real-time answer generators like ChatGPT or Copilot, or automated note-taking bots) during interviews.
These tools must not be used to record, assist with, or enhance responses in any way. Our interviews are designed to evaluate your individual experience, thought process, and communication skills in real time. Use of AI tools without prior instruction from the interviewer will result in disqualification from the hiring process.
This position may require access to technology and/or software subject to U.S. export control laws and regulations, including the Export Administration Regulations (EAR). As such, applicants must be eligible to access export-controlled information as defined under applicable law. Marvell may be required to obtain export licensing approval from the U.S. Department of Commerce and/or the U.S. Department of State. Except for U.S. citizens, lawful permanent residents, or protected individuals as defined by 8 U.S.C. 1324b(a)(3), all applicants may be subject to an export license review process prior to employment.
#LI-AO1
