Strong understanding of LLM pre-training/post-training, AI inference/serving, and memory/storage hierarchies.
Ability to translate AI system requirements into hardware/software architecture decisions.
Experience in Agentic AI workload analysis, including token and context management.
Proficiency in analytical modeling, statistical methods, and Python-based analysis.
Expertise in signal integrity and power integrity analysis for AI systems.
Knowledge of optical interconnects and advanced packaging technologies.
Responsibilities
Lead architecture reviews and scenario development for AI workloads.
Define requirements and evaluate trace data for modeling accuracy.
Deliver comprehensive documentation including Traceability Matrix and Workload Catalog.
Evaluate next-gen AI memory architecture requirements, focusing on SI/PI and optical interconnects.
Analyze trade-offs in bandwidth, latency, and power across memory and interconnect solutions.
Benefits
Top-tier health insurance at no employee cost.
Generous paid time off including holidays and parental leave.
401k matching to support retirement savings.
Flexible Spending Account options for healthcare and dependent care.
Educational reimbursement up to $10,000 annually.
Donation matching and volunteering opportunities.
Corporate discount programs for employees.
Complimentary meals provided throughout the day.
Full Job Description
Job Title: AI Solution Architecture Director Office Location: San Jose, CA Job Type: Full-Time Work Model: Onsite
Job Summary:
Bridge evolving customer AI workloads with memory/storage requirements and quantitative comparisons.
Secure local expertise in architecture design, analysis, modeling, and technical alignment across HBF validation and Path Finding.
Responsibilities:
Lead Architecture Reviews (for ARD), scenario development, and trace analysis.
Define requirements, evaluate trace data, and analyze modeling errors.
Deliver ARD Traceability Matrix, Workload Catalog, Trace Manifest, and Model/Parameter Sheets with version control.
Evaluate SI/PI, optical interconnect, and advanced packaging requirements for next-generation AI memory architectures.
Analyze bandwidth, latency, power, and signal integrity trade-offs across memory, interconnect, and packaging solutions.
Qualifications:
Strong understanding of LLM pre-training/post-training(SFT, RL), AI inference/serving, memory/storage hierarchies, data movement, and bottleneck analysis.
Ability to translate AI system requirements into HW/SW architecture decisions and ARD(Architecture Requirement Documentation) traceability.
Experience in Agentic AI/Inference workload analysis, including Token, Context, KV Cache, Weights, Activations, and Trace/Profiling.
Proficiency in analytical/system modeling, statistical methods, Python-based analysis, and prediction/validation error analysis.
Expertise in SI/PI, high-speed interfaces, and signal/power integrity analysis for AI and memory systems.
Knowledge of optical interconnects and advanced packaging technologies, including 2.5D/3D integration and chiplet architectures
Benefits:
Top Tier health insurance at no employee cost
Paid day offs: Paid Time Off, Company Holidays, Parental Leave, Happy Fridays
401k Matching
Flexible Spending Account (FSA) for Health Care & Dependent Care
Educational reimbursement up to $10,000 per year
Donation Matching and volunteering opportunities
Corporate discount programs
Free Breakfast/Lunch/Dinner provided to employees
Compensation:
Our compensation reflects the cost of labor across several U.S. geographic markets, and we pay differently based on those defined markets. Pay within the provided range varies by work location and may also depend on job-related skills and experience. Your Recruiter can share more about the specific salary range for the job location during the hiring process.
