Technical Director, Large-Scale AI Model Inferencing

Please Note:

To provide the best candidate experience amidst our high application volumes, each candidate is limited to 10 applications across all open jobs within a 6-month period. 

Advancing the World’s Technology Together

Our technology solutions power the tools you use every day--including smartphones, electric vehicles, hyperscale data centers, IoT devices, and so much more. Here, you’ll have an opportunity to be part of a global leader whose innovative designs are pushing the boundaries of what’s possible and powering the future. 

We believe innovation and growth are driven by an inclusive culture and a diverse workforce. We’re dedicated to empowering people to be their true selves. Together, we’re building a better tomorrow for our employees, customers, partners, and communities.

 What You’ll Do

Inference is becoming a memory-bandwidth business. As models scale past what any single GPU can hold — KV caches grow with context, MoE expert weights spill beyond HBM, and new architectures change the rules of what "model state" even means — the winners will be the companies that treat memory as the core product of AI inference, not an afterthought.

We are looking for a Hands-on Principal Engineer who combines deep, first-principles knowledge of AI model architectures (dense Transformers, Mixture-of-Experts, State Space Models, and hybrids) with production-scale inference expertise, to own the requirement for full-stack AI memory solutions at scale — spanning GPU HBM, host DRAM, CXL-attached memory pools, and NVMe/SSD tiers and Samsung Cognos, AI memory software that moves model state intelligently across them.

This person will be the technical authority who connects model behavior to memory-system design: someone who can explain why an MoE router's activation pattern dictates an LRU expert cache policy, why a Mamba state cache breaks the assumptions of PagedAttention, and why disaggregated prefill/decode changes the required memory bandwidth per token by an order of magnitude — and then build the products that exploit those facts.

Location: Daily onsite presence at our San Jose office/headquarters in alignment with our Flexible Work policy

Job ID: 43027

Model Architecture Expertise — The Foundation

• Serve as expert on how different model families consume and move memory, and translate that into memory-product requirements:
  • Dense Transformers: MHA/MQA/GQA/MLA attention, KV-cache growth characteristics, long-context behaviors, attention sinks and prefix locality.
  • Mixture-of-Experts: routed vs. shared experts, expert-parallel execution, routing skew and hot-expert locality, expert-weight offloading and cache-admission policies, per-token weight-read economics.
  • State Space Models (Mamba/Mamba-2) and hybrid SSM-attention architectures: recurrent state vs. KV cache semantics, state size per sequence and per layer, cache-swapping behavior for context switching and batching, and what "cache-aware scheduling" means when the state is a fixed-size tensor instead of a token-indexed table.
  • Emerging architectures: linear attention, sliding-window/hybrid layers, diffusion and multimodal transformers — and how each changes the memory hierarchy math.
• Model the memory footprint, bandwidth demand, and access patterns of frontier open-weight models (e.g., Llama/Qwen-class dense, DeepSeek/Kimi-class MoE, Jamba-class hybrids) and publish internal reference architectures for each.
• Track the model landscape as a roadmap input: anticipate what coming architectures (longer contexts, agentic multi-session reuse, reasoning-loop workloads, speculative decoding drafts) will demand from memory systems 12–24 months out.

Large-Scale Inference Expertise

• Own deep expertise in production inference stacks — SGLang (HiCache), vLLM (PagedAttention, LMCache integration), NVIDIA Dynamo, TensorRT-LLM, llama.cpp-class engines — including their memory-management internals, not just their flags.
• Drive inference performance engineering: continuous batching, chunked prefill, disaggregated prefill/decode, prefix and radix caching, speculative decoding, CUDA Graphs, and their interactions with memory tiering.
• Own the latency/throughput/cost envelope: TTFT and TBT/TPOT SLOs, tokens-per-second per dollar, GPU memory utilization as the binding constraint, and the tradeoff curves between cache hit rate, memory capacity, and bandwidth.
• Define benchmarking and characterization methodology: realistic agentic and long-context workloads (multi-turn reuse, session persistence, RAG prefixes), KV-cache reuse-rate measurement, and bandwidth-latency profiling across the full hierarchy (Nsight, PyTorch Profiler, vendor memory tools).

Full-Stack AI Memory Solutions — The Core Mandate

• Define engineering requirements, with proof, for tiered memory systems for inference at fleet scale: HBM as L1, host DRAM (pinned, NUMA-aware pools) as L2, CXL-attached memory pools as an elastic tier, and NVMe/SSD as capacity tier — with the policies (admission, eviction, prefetch, placement) that make the hierarchy behave like one memory.
• Design expert-weight offloading solutions for MoE serving: host-resident expert pools, GPU-resident expert caches with bandwidth-adaptive fill/evict policies, and CPU/CXL-execution hybrid paths — informed by the routing statistics of real models.
• Translate model knowledge into product: write the requirements, reference architectures, and performance models that guide memory hardware and firmware roadmaps (HBM capacity/bandwidth, CXL device behavior, SSD QoS for cache tiers), and validate with end-to-end prototypes on real inference workloads.
• Develop and Deliver POCs: demos and published benchmarks showing inference TCO improvement from the memory stack — e.g., context capacity multiplied at constant GPU count, or cost-per-token reduced through cache-hit-rate gains — credible to both CTOs and PhD researchers.

Technical Leadership

• Set multi-year technical strategy for AI memory solutions; own build-vs-adopt-vs-contribute decisions across the open-source inference and caching ecosystem (vLLM, SGLang, LMCache, Cognos-style KV stores) and drive upstream contributions where strategic.
• Lead architecture reviews and deep-dive design sessions; write the documents that become the company's standard for how we talk about memory for AI.
• Represent the company with customers and partners at the deepest technical level: serve as the expert voice in CTO-to-CTO conversations, design wins, and standards discussions.
• Mentor senior engineers and grow a bench of architecture talent across the model-to-memory boundary.

What You Bring

• BS in Computer/Electrical/Electronic Engineering or Computer Science, and 20 years of relevant experience MS in Computer/Electrical/Electronic Engineering or Computer Science with 18 years of relevant experience preferred.
• 12+ years in systems engineering, with 4+ years hands-on in large-scale LLM inference or GPU systems performance — you have personally profiled, diagnosed, and fixed memory bottlenecks in production serving, not just read about them.
• First-principles understanding of transformer-class model internals: you can derive KV-cache size formulas from attention math, explain MQA/GQA/MLA tradeoffs, and reason about activation-memory peaks during prefill.
• Working expertise with MoE model behavior: routing, expert parallelism, load skew, and the weight-memory economics of serving models larger than GPU capacity.
• Direct experience with at least one major inference stack's memory-management internals (vLLM PagedAttention/block manager, SGLang HiCache/token pools, TensorRT-LLM KV manager, or llama.cpp compute buffers) — code-level, not configuration-level.
• Strong performance-engineering skills: bandwidth-bound vs. compute-bound analysis, NUMA and PCIe topology reasoning, RDMA basics, and fluency with GPU/CPU profilers.
• Track record of building systems software at the memory/storage/IO layer — caches, tiering, paging, or storage engines — with production deployments.
• Ability to write models and simulators, not just measure: analytical queueing, cache-hit-rate, and bandwidth models that predict system behavior before hardware exists.
• Excellent written and verbal communication, including executive-level technical narrative; comfort being the technical face of the company in front of customers.

Preferred

• Experience with State Space Model or hybrid SSM-attention serving (Mamba-class state management, cache swapping for recurrent models) — rare and highly valued.
• Contributions to open-source inference/caching projects (vLLM, SGLang, LMCache, HiCache, Mooncake, KTransformers, llama.cpp).
• Experience with CXL memory pooling, CXL-attached tiering, or near-memory processing in real deployments or serious prototypes.
• Experience with SSD/NVMe as a KV or expert cache tier, including QoS engineering for inference-grade latency.
• Background in memory/storage product companies bringing hardware-software co-designed solutions to market.
• You’re inclusive, adapting your style to the situation and diverse global norms of our people. 
• An avid learner, you approach challenges with curiosity and resilience, seeking data to help build understanding. 
• You’re collaborative, building relationships, humbly offering support and openly welcoming approaches. 
• Innovative and creative, you proactively explore new ideas and adapt quickly to change.

#LI-SF1219

Equal Opportunity Employment Policy 

Samsung Semiconductor takes pride in being an equal opportunity workplace dedicated to fostering an environment where all individuals feel valued and empowered to excel, regardless of race, religion, color, age, disability, sex, gender identity, sexual orientation, ancestry, genetic information, marital status, national origin, political affiliation, or veteran status.

When selecting team members, we prioritize talent and qualities such as humility, kindness, and dedication. We extend comprehensive accommodations throughout our recruiting processes for candidates with disabilities, long-term conditions, neurodivergent individuals, or those requiring pregnancy-related support. All candidates scheduled for an interview will receive guidance on requesting accommodations.

Our Commitment to Innovation and Fairness

At Samsung Semiconductor, we use Artificial Intelligence (AI) tools in the recruitment process to enhance efficiency. However, AI is used as a support tool, not a final decision-maker. All hiring decisions are made by our human recruiting team and hiring managers to ensure every candidate is evaluated fairly and holistically.

Recruiting Agency Policy

We do not accept unsolicited resumes. Only authorized recruitment agencies that have a current and valid agreement with Samsung Semiconductor, Inc. are permitted to submit resumes for any job openings.

Applicant AI Use Policy 

At Samsung Semiconductor, we support innovation and technology. However, to ensure a fair and authentic assessment, we ask that candidates rely on their own knowledge and skills throughout the process. AI tools may be used for basic preparation, grammar, and research, but should not be used to generate or assist with submitted content or live interview responses. If we determine that AI is being used outside these guidelines, we reserve the right to pause or end the interview, and your candidacy may be disqualified.

Trade Secret Notice

By submitting an application, you agree not to disclose to Samsung—or encourage Samsung to use—any confidential or proprietary information (including trade secrets) belonging to a current or former employer or other entity.

Applicant Privacy Policy
https://semiconductor.samsung.com/about-us/careers/us/privacy/