Hi, my name is

Arya Raeesi.

M.Sc. student in Electronic Systems Design and Innovation at NTNU, including a one-year graduate exchange at UC Berkeley EECS. Experience from the NASA Small Explorers (SMEX) Program, Qualcomm (incoming), the Cornell Natural Language Processing Group, Sony Europe, and Nordic Semiconductor (incoming), with projects involving institutions across North America, Europe, and Asia. My work sits at the intersection of machine learning systems and hardware design: LLM inference and serving, evaluation and auditing of language models, and low-power inference accelerators.

View my work Get in touch

CV LinkedIn GitHub Google Scholar

01. Projects

Research Engineering

▸ Ongoing

AI · EE

Aug 2026 – Dec 2026

RISC-V ML Inference Co-Processor for Ultra-Low-Power Wireless SoCs

Extending a custom SystemVerilog pre-processing accelerator for ML into a dedicated inference co-processor, unifying pre-processing and inference in a single peripheral unit to support a parallel RISC-V ML ISA extension. Targeting on-device ML for ultra-low-power wireless SoCs.

Affiliation

Nordic Semiconductor ASA

Partners

Keywords

SystemVerilog
RISC-V
ISA Extensions
Hardware Accelerators
ML Inference
On-Device ML
RTL Design
Ultra-Low-Power Design
Hardware-Software Co-Design

AI · SWE

Jul 2026 – Ongoing

Deleted but Not Gone: Auditing Erasure in Memory-Augmented Language Models

Extending my causal audit framework for machine unlearning [arXiv:2607.00605] to Co-LMLM's dense external memory, in direct collaboration with its authors. HALO runs each fact through three exact memory interventions to test whether deletion truly removes it — probing behavioral survival, representational leakage, and adversarial recovery. Provable deletion is a core requirement for AI safety, privacy compliance, and trustworthy AI deployment.

Affiliation

Cornell Natural Language Processing Group

Partners

Keywords

LLMs
NLP
Externalized Memory
Machine Unlearning
Knowledge Editing
Retrieval
Python
PyTorch
CUDA

▸ Research

AI · SWE

Aug 2025 – Aug 2026

Tagging the Positron Sky: A Naive Bayes Classifier for β+ Decay

Conducted research on gamma-ray astrophysics using high-purity germanium detector data as part of the COSI (Compton Spectrometer and Imager) mission. Built a Naive Bayes classifier from scratch, including feature extraction, density-matrix likelihood, Bayes-rule decision, and evaluation pipeline. Exploring potential applications of neural networks for similar problems.

Affiliation

NASA Small Explorers (SMEX) Program / UC Berkeley Space Sciences Laboratory

Partners

Keywords

Naive Bayes Classifier
Event Reconstruction
Gamma-Ray Astrophysics
Compton Physics
High-Purity Germanium Detectors
Physics-Informed Machine Learning
Maximum Likelihood Estimation
Python
C++
PyTorch
MEGAlib
Geant4
ROOT

AI · SWE

Feb 2026 – May 2026

Compositional Analysis for Safety Specifications

This project extends compositional statistical model checking for autonomous vehicles from Markovian to non-Markovian safety specifications by augmenting simulation states with DFA states and propagating the DFA distribution across primitive scenario traces.

Affiliation

UC Berkeley

Partners

Report

Manuscript

Keywords

Compositional Analysis
Statistical Model Checking
DFA
Automata Theory
Markov Chains
Python
VerifAI
MetaDrive
CARLA
Webots
Scenic

AI · SWE

Feb 2026 – May 2026

Auditing Forgetting in Limited Memory Language Models

Causal evaluation framework for memory separation in Limited Memory Language Models (Zhao et al., 2025). Decomposes post-deletion correctness into parametric leakage, retrieval-mediated correctness, and retrieval artifacts across 1404 datapoints, six prompt formulations, and thirteen database variants.

Affiliation

UC Berkeley

Partners

Report

arXiv preprint arXiv:2607.00605

Keywords

Machine Unlearning
Knowledge Editing
Causal Inference
Python
PyTorch
CUDA
LLMs
NLP
Slurm
Weights & Biases

AI · SWE

Sep 2025 – Dec 2025

Beyond Binary Priorities: Multi-Tier SLA Scheduling for LLM Serving

Multi-priority extension to Llumnix (OSDI 2024) enabling fine-grained SLA differentiation for multi-tenant LLM inference while preserving low tail latency. Achieved up to ~3× P99 latency improvement, with diminishing returns beyond four priority tiers.

Affiliation

UC Berkeley

Partners

Report

Manuscript

Keywords

Priority Scheduling
SLO-aware Scheduling
KV-Cache Management
Live Migration
Tail Latency Optimization
Discrete-Event Simulation
Python
Vidur
LLM Serving
Slurm
Weights & Biases

Jan 2025 – Jun 2025

Deep Learning for Segmentation of Hyperspectral Satellite Images

Trained convolutional neural networks for sea, land, and cloud classification of hyperspectral satellite images from the HYPSO-2 mission. Used NVIDIA GPU cluster acceleration to optimize performance and training speed.

Affiliation

NTNU SmallSat Lab

Partners

Roger Birkeland (Advisor)

Report

Manuscript

Keywords

Hyperspectral Imaging
Semantic Segmentation
Convolutional Neural Networks
Lightweight Models
Earth Observation
Spectral Signatures
Python
PyTorch
CUDA
ENVI 5

▸ Engineering

AI · SWE

Mar 2026 – Mar 2026

Type-Aware Hybrid RAG for Factoid QA

Retrieval-augmented QA system over UC Berkeley EECS web content. Built a 192-question benchmark from a crawled 8,417-document corpus, with a RAG pipeline combining BM25 retrieval, type-aware reranking, instruction-tuned generation, and a deterministic extractive fallback.

Affiliation

UC Berkeley

Partners

Report

Manuscript

Keywords

NLP
RAG
LLMs
BM25
BFS Crawl
Query Expansion
Slot Filling
Python
Slurm

Sep 2025 – Dec 2025

Four Stages, Two ISAs: A Pipelined RV32IF Core on PYNQ-Z1 FPGA

Pipelined RISC-V SoC on the Digilent PYNQ-Z1 implementing an RV32I core with CSR support and a pipelined RV32F floating-point unit. Reached 58 MHz with ~1.16 integer CPI, ~1.83 FP CPI, and an FOM of 12.3.

Affiliation

UC Berkeley

Partners

Lawrence Rhee

Keywords

Verilog
Xilinx Vivado
RISC-V
FPGA
PYNQ-Z1
RTL Design
Hardware-Software Co-Design
ISA Compliance Testing

SWE · EE

Jun 2025 – Aug 2025

Automated Test-Evaluation System for Automotive Image Sensors

Designed and implemented an automated test-evaluation software system for automotive image sensors, focusing on efficient data storage, repeatable test procedures, and system-level reliability. Output structured in alignment with industry standards such as EMVA 1288 to enable consistent sensor evaluation across revisions.

Affiliation

Sony Europe

Partners

Vegard Havellen (Advisor)

Keywords

Image Sensors
Data Analysis
Data Validation
Python
REST APIs
EMVA 1288
Image Sensors
Docker
Vue
TypeScript
Django
PostgreSQL

Apr 2025 – May 2025

Resolution and Robustness of a Three-Microphone DOA System

Direction-of-arrival estimation system using three omnidirectional microphones in an equilateral triangle, sampled via MCP3201 ADCs into a Raspberry Pi. Cross-correlation-based time-delay estimation gives sub-2° average accuracy under nominal conditions, with degraded behaviour at 270° and 300°.

Affiliation

NTNU

Partners

Truls Østvedt

Report

Lab report

Keywords

C
Python
Raspberry Pi
MCP3201 ADC
Digital Signal Processing (DSP)
Cross-Correlation
Time-Delay Estimation

SWE

Jan 2025 – Apr 2025

DrawGuess: Multiplayer Pictionary Reinvented

Turn-based multiplayer Pictionary game for Android. Real-time drawing and guessing across networked clients with a competitive point-based scoring system, built with LibGDX and Firebase.

Affiliation

NTNU

Partners

Report

Implementation report

Keywords

Software Architecture
Design Patterns
Entity-Component-System
Client-Server Architecture
State Synchronization
Modifiability
Java
LibGDX
Android SDK
Firebase Firestore
Firebase Storage
Socket.IO
Render

Jan 2025 – Feb 2025

Quantization-Limited SNR on a 12-bit Multi-ADC Pipeline

Measurement and analysis of the SNR of a multi-ADC analog signal pipeline using a Raspberry Pi 3B with MCP3201 ADCs and a low-pass filter front end. Theoretical 12-bit SNR (~74 dB) compared against empirical measurements (~55 dB) at 1, 2, and 10 kHz.

Affiliation

NTNU

Partners

Truls Østvedt

Report

Lab report

Keywords

Digital Signal Processing (DSP)
Quantization
Noise Analysis
Fast Fourier Transform (FFT)
C
Python
Raspberry Pi
MCP3201 ADC

SWE · EE

Jan 2024 – May 2024

MediCare: Temperature, Time, Tracking

Three-part medication-storage system for the Physical Medicine outpatient clinic at St. Olavs Hospital: a fridge temperature monitor with web dashboard and SMS alerts, an open-vial holder that tracks 3-day usability with LED indicators, and a rotating rack for unopened vials that surfaces the next-to-expire medication.

Affiliation

NTNU

Partners

Report

Project report

Keywords

IoT
Electromechanical Systems
Embedded Systems
C
Python
Raspberry Pi
BME680
MySQL
Node.js
React
TypeScript

SWE

Dec 2022 – Feb 2023

End-to-End Client Acquisition System

Custom CRM and client acquisition engine integrating the Brønnøysund Register and three phone registries (1881, 180, Gule Sider) for automated data enrichment and contact verification. Saved ~450 hours/year and reduced third-party API costs by ~$10,000.

Affiliation

BlinkWeb

Keywords

CRM
Data Enrichment
Data Validation
Python
REST APIs
MySQL
Web Scraping

02. Get in Touch

I'm open to interesting conversations and collaborations. Drop me a line and I'll get back to you as soon as possible.

aryar at stud dot ntnu dot no