Emmanouil Ioannis Farsarakis

Systems Architect & AI Researcher — Intel
Edinburgh, United Kingdom
Eligible to work in the US, UK & EU

I am a systems architect and AI researcher in Intel's Systems Architecture and Engineering team, working on inference-oriented, memory-centric system architectures — disaggregated and in-network memory, KV-cache placement across heterogeneous memory, and the serving of vision-language-action (VLA) models for robotics on dataflow and heterogeneous accelerators. My background is in physics and high-performance computing, and I have spent more than a decade at the intersection of computer systems, AI infrastructure and performance, across both industry and academia. The throughline: the FLOP/s-versus-TB/s balancing act, applied recursively at every layer of the memory hierarchy.

Publications & Patents

2024 Optimizing Graph Learning using Hierarchical Graph Adjacency Matrix (HGAM) Journal R. Benke, E. I. Farsarakis, M. Szarmach, A. Zanetti, H.-H. S. Lee — TASK Quarterly 28(3)
2023 Characterizing the Scalability of Graph Convolutional Networks on Intel® PIUMA M. Adiletta, J. J. Tithi, E. I. Farsarakis, G. Gerogiannis, R. Adolf, R. Benke, et al. — IEEE ISPASS 2023
2020 Edinburgh's submissions to the 2020 machine translation efficiency task N. Bogoychev, R. Grundkiewicz, A. F. Aji, M. Behnke, K. Heafield, S. Kashyap, E. I. Farsarakis, M. Chudyk — WNGT 2020 (pp. 218–224)
2017 Resource requirement specification for novel data-aware and workflow-enabled HPC job schedulers E. Farsarakis, I. Panourgias, A. Jackson, J. Herrera, M. Weiland, M. Parsons — SC'17, PDSW-DISCS
2016 Monitoring and evaluating I/O performance of HPC systems M. Farsarakis, M. Weiland, W. Jackson, M. Parsons — 4th Intl. Exascale Applications and Software Conf. (EASC)
2015 Experiences Porting Production Codes to Xeon Phi Processors E. Farsarakis, A. Jackson, F. Reid, D. Scott, M. Weiland — Parallel Computing: On the Road to Exascale (pp. 575–583)
2014 Energy Efficiency: Benefits and limitations of modern HPC architectures E. I. Farsarakis — MSc dissertation, EPCC, The University of Edinburgh

Experience

IntelNov 2023 – Present
AI Systems & Solutions Engineer · Systems Architecture & Engineering — Edinburgh (remote)

Technical lead for SPEC Cloud benchmark simulation and system-level performance projection, leading a team of five. Drive next-generation, inference-focused architecture research for large-memory-capacity serving — silicon photonics and rack-scale optical interconnects, dataflow vs. heterogeneous accelerators, disaggregated and in-network memory, and VLA-model serving for robotics.

IntelFeb 2022 – Nov 2023
Artificial Intelligence Researcher — Edinburgh (remote)

Coordinated research with leading scientists on next-generation AI algorithms — GNNs, NLP and recommendation systems — for graph analytics and security.

IntelFeb 2019 – Feb 2022
Platform Architect — Edinburgh (hybrid)

Drove novel AI optimizations (SIMT, sparse-compute acceleration, quantization) and led AI workload characterization for the Intel PiUMA sparse accelerator. Based at the University of Edinburgh, collaborating with K. Heafield and P. Boyle.

The University of Edinburgh — EPCC2014 – 2019
Applications Consultant / Developer

HPC and data-science leadership across finance, cyber security and exascale; porting, profiling and optimisation on academia–industry collaborations.

Selected Projects

Inference Architectures for VLA Robotics

Characterized vision-language-action robotics models (π0.5, GR00T) as a two-frequency serving workload and mapped them onto candidate architectures, comparing dataflow accelerators (Groq) against heterogeneous GPUs — a common FLOP/s-versus-TB/s balancing act across the memory hierarchy.

Silicon Photonics & Disaggregated Memory

Assessed silicon-photonics and rack-scale optical interconnect technologies (e.g. Celestial AI) for memory-centric inference, comparing latency, throughput and cost across on- vs off-chip solutions; explored disaggregated compute/memory and in-network memory.

Sparse Computational Infrastructure for GNNs Harvard × Intel

Established and led a cross-organisation collaboration — around seven contributors across Intel, Intel Labs and Harvard University (SEAS) — on graph-learning acceleration for Intel PiUMA. Owned inception, stakeholder management, software development and performance optimization — resulting in ISPASS 2023, a TASK Quarterly journal paper (2024) and a US patent.

Low-Precision CPU Inference — Marian NMT in SPEC CPU

Part of the Intel–University of Edinburgh collaboration (K. Heafield) on CPU-efficient, low-precision (int8) Marian neural machine translation, which won the 2020 NGT efficiency task. The underlying int8 GEMM kernels were adopted into the SPEC CPU benchmark in 2026 — where Marian machine translation is the sole NLP workload.

NextGenIO — Exascale Non-Volatile Memory

Built system-level workload characterization of ARCHER (UK national supercomputer) and researched data-aware, workflow-enabled HPC scheduling (SLURM-class) for Intel 3D XPoint non-volatile memory.

ISC'14 Student Cluster Competition — Highest Linpack

Designed and optimized the software stack of a custom GPU cluster — Highest Linpack at ISC'14 (3.38 Tflops/kW, est. 4th on the June 2014 Green500). Ported GADGET-3 kernels to GPU via OpenACC for 2× speedup.

Education

MSc in High Performance Computing2014
The University of Edinburgh — Distinction; Class Representative
BSc Physics (Computational Science specialization)2011
University of Crete — Top 5% of class