Field Application Engineer – Enterprise and Hyperscalers

Advanced Micro Devices, Inc•Austin, TX

About The Position

At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond. Together, we advance your career. We are seeking a Field Application Engineer to join the Centre of Excellence (CoE) group to support our largest hyperscale, mega data center, and enterprise customers. The role broadly involves: Close technical collaboration with customers and partners in support of framework agreements and RFP-driven requests. Providing hands-on support to customers and partners to enable and demonstrate optimal performance of critical workloads on current and future AMD Instinct GPUs, EPYC CPUs, or Pollara network cards Example workloads, but not limited to: Apache Spark, Databricks, Apache Kafka, vector databases, key-value databases Modeling competitive positioning Creating a body of technical documentation of performance best practices on AMD hardware to support the Field Application team, partners, and customers This is a ‘hand-on’ technical role and we are looking for an individual with an established background in application performance characterization, coupled with an understanding of the effects of the underlying hardware. In addition to technical investigations, you will also need to be able to create and deliver presentations and training both remotely and in person to our customers and partners. The role is based within the USA and will require approximately 20% travel to customers and conferences both nationally and internationally.

Requirements

You have customer-facing experience and enjoy collaborating with customers and partners; you are able to communicate at a level appropriate from CxO to engineer.
You have a solid understanding of server system architecture (CPU, DRAM, PCI, BIOS)
You are comfortable with basic Linux system administration (high level of comfort setting up and managing a Linux-based system, troubleshooting, configuring boot parameters, kernel parameters, etc.)
You have demonstrated capability to run benchmarks and generate repeatable results, and to document the methodology and results for reproducability
You are proficient in utilizing profiling tools (e.g. Linux Perf, vendor proprietary tools) to characterize application performance
You have a strong positive can-do attitude and are willing to do what is necessary and lead others in the wider FAE team by example. Available to help colleagues.
You are skilled in independently prioritizing opportunities to deliver results on time
You possess excellent verbal and written communication skills

Nice To Haves

Knowledge of CPU pinning, NUMA optimization, I/O tuning (both disk and network)
Experience identifying how silicon / CPU features affect performance of Spark or database workloads (e.g. where does clock speed help? Where does memory latency help? Where does L2 cache size help? Etc.) - explain observed performance, not just report on it.
Experience with public cloud Infrastructure as a Service offerings - Azure, AWS, Google and/or Oracle Cloud
Understand how the software stack affects performance: frameworks, precision, compilers, libraries, and other accompanying middleware applications.
Experience deploying containerized applications in Kubernetes
Hands-on AI experience within automotive, finance, enterprise, defense verticals
Application experience compiling codes from source (e.g. HPC)
Programming experience with any of HIP, CUDA, Python, C/C++, Fortran, OpenACC, OpenMP, pSTL
Understanding impact of inter-node network choices on performance at scale.
Creating performance projections for applications.
Any experience understanding/inspecting/writing assembly
Understanding of memory and cache hierarchy and methods to query performance/latency at each level.
Inspecting and dataflow down to the register-level
Government level security clearance

Responsibilities

Support winning new business within the Enterprise and Mega Data Center verticals.
Enabling customers to execute their workloads predominantly on AMD server products: EPYC CPU, Instinct GPU, and Pollara network cards.
Liaise with and advise customers and partners through Proof of Concepts, presentations, and training. Support RFP responses.
Engineering: execute popular and customer-specific workloads, generate results.
Characterize application performance on AMD products.
Understand how system and software choices affect performance.
Compare performance to our competition.
Model projected performance based on future hardware specifications.
Build a body of documentation for internal and external dissemination: AMD-internal guides, whitepapers, tuning guides, training collateral.
Proactive engagement across AMD teams: CPU/GPU/Network Business Units, Engineering, Architecture, Platform, Software, and Product Development teams providing feedback and leadership from the field on requirements.
Gathering missing functionality and working with Engineering to resolve and test.
Assist in creating Total Cost of Ownership models to aid pricing strategies
Technically owning and resolving customer and partner issues.
Submitting JIRA tickets and driving resolution.