.png){kind=logo}
About the Role
Majestic Labs builds power-efficient AI servers for the largest and most advanced AI workloads.
We are looking for a Senior Architect to work on simulation and translating architectural ideas into quantitative, defensible performance models.
This role is ideal for someone who lives at the intersection of:
- Computer architecture
- Workload characterization
- System-level modeling
- AI / data-intensive workloads
What You’ll Do
- Performance simulator & translate workloads into models
- Extend and maintain system-level performance models (compute, memory, interconnect, scheduling).
- Model system behaviors: NUMA effects, contention, coherence, bandwidth saturation.
- Characterize real workloads (LLMs, GNNs, graph analytics, tabular models and more).
- Guide architectural decisions
- Evaluate architectural trade-offs
- Produce quantitative comparisons vs. existing and emerging AI platforms.
- Work closely with hardware architects, compiler/runtime teams, and external partners.
- Ensure simulator assumptions align with hardware and software reality.
- Support external conversations
- Contribute to technical deep dives with strategic partners and customers.
- Help translate performance modeling into clear narratives for execs and investors.
What We’re Looking For
Required
- BSc in CS, EE, CE or similar degrees plus 8 years experience in computer architecture, systems research, or performance engineering. Or PhD in CS, EE, CE or similar degrees plus 2 years of relevant experience.
- Strong background in performance modeling or simulation (analytical, event-driven).
- Experience with AI or graph workloads.
- Understanding of: memory hierarchies (NUMA, caches, coherence), Interconnects (PCIe, fabrics, RDMA-), GPU-based systems.
- Hands-on coding experience (Python, C/C++, or similar).
- Ability to reason from first principles, not just benchmarks.
Strong Plus
- Background in architecture simulators ( gem5-like, in-house tools, or research frameworks).
- Exposure to ML runtimes, compilers, or hardware-aware model design.
- Research background (MS/PhD) in computer systems (CS/EE), architecture, or related fields.
Skills Required
- BSc in CS, EE, CE or similar plus 8 years experience, or PhD in CS, EE, CE or similar plus 2 years relevant experience
- Strong background in performance modeling or simulation (analytical, event-driven)
- Experience with AI or graph workloads (LLMs, GNNs, graph analytics, tabular models)
- Understanding of memory hierarchies (NUMA, caches, coherence)
- Understanding of interconnects (PCIe, fabrics, RDMA) and GPU-based systems
- Hands-on coding experience in Python, C/C++, or similar
- Ability to reason from first principles rather than relying solely on benchmarks
- Background in architecture simulators (gem5-like, in-house, or research frameworks)
- Exposure to ML runtimes, compilers, or hardware-aware model design
- Research background (MS/PhD) in computer systems, architecture, or related fields
What We Do
Majestic Labs is reimagining AI infrastructure for the world’s most demanding workloads. Today, organizations are forced to overprovision expensive compute just to access the required memory their models need. We took a fundamentally different approach by pairing a massive amount of compute with 1000x the memory to create game changing improvements in performance, power and deployment efficiency. Our customers can literally replace racks of traditional AI infrastructure with a single Majestic server.
