Simone Zamboni

Machine Learning Research Engineer

Embark Studios

Biography

Currently Machine Learning Research Engineer at Embark Studios AB, researching how to use large language models to make video game characters come alive.
Previously Machine Learning developer at Substorm, to help companies implement AI and NLP solutions using Python, Deep Learning and AWS.
Graduated with a double degree in Autonomous Systems, a program focused on Artificial Intelligence and Robotics, between the University of Trento (Italy) and KTH in Stockholm.
Accomplishments include publishing a journal research article based on my master thesis at SCANIA and presenting advancements on language models for video game characters at conferences.

Download my resumé.

Interests

Artificial Intelligence (AI)
Natural Language Processing (NLP)
Computer Vision (CV)
Reinforcement Learning (RL)
Sequence Prediction

Education

Double Master Degree in Autonomous Systems

University of Trento (first year), KTH Royal Institute of Technology (second year)
Bachelor's Degree in Information and Business Organization Engineering

University of Trento

Skills

Python

also with Numpy and Pandas

Large Language Models

with the Transformers library

Deep Learning

with Pytorch and Keras/TensorFlow

Machine Learning

with Scikit-learn

GIT

Version Control

AWS and GCP

Docker

Terraform

Cloud resources management

Rust

Experiences

Machine Learning Research Engineer

Embark Studios

Mar 2022 – Present Stockholm

Machine Learning Research Engineer at the video game company Embark Studios, researching how to use large language models to make video game characters come alive. My responsibilities include: keeping up to date with the latest research, fine-tuning language models with python and Pytorch, help with their deployment and develop on the game client which is written in rust.

Machine Learning Developer

Substorm

Nov 2020 – Mar 2022 Stockholm

Machine Learning Developer at Substorm AB, a young consultancy company specialized in AI. My experience was mainly in Natural Language Processing(NLP): Python, Pytorch, TensorFlow/Keras, Scikit-learn, Numpy and Pandas for development and AWS, Docker, Azure Pipelines and Terraform for deployment. Additionaly, I supervised a master thesis student from KTH on a deep Reinforcement Learning thesis project.

Machine Learning Engineer Intern

Scania

Jan 2020 – Jun 2020 Södertälje

Master thesis intern in the SCANIA Autonomous Driving Research section. My thesis project was about pedestrian trajectory prediction with deep neural networks. During my research I achieved state-of-the-art performances on a publicly available dataset and I now publishedmy thesis as an article in the journal Pattern Recogniton (https://doi.org/10.1016/j.patcog.2021.108252).

Software Developer Intern

Okkam

Feb 2018 – Jun 2018 Trento (Italy)

Bachelor thesis internship in which I developed a proximity marketing Android app to inform users of interesting restaurants nearby using Bluetooth.

Back-end Developer

DW inormatica

Jul 2017 – Oct 2017 Verona (Italy)

Summer assignment in the Internet of Things field, in which I developed a modular Node.js REST API server that collects and cleans data coming from devices that use different protocols such as LORA, Wireless Meter Bus and TCP/IP. The experience also included prototyping with Arduino, and one of those prototypes was a small meteorological station.

Education

Double Master Degree in Autonomous Systems

KTH, University of Trento

Sep 2018 – Jul 2020 Stockholm, Trento(Italy)

Double Master Degree between the University of Trento, for the first year, and the Royal Institute of Technology (KTH), for the second year, focused on Artificial Intelligence, Robotics and Entrepreneurship. Topics addressed include: machine learning, deep learning, reinforcement learning, robotic design, robotic path planning and start-up business development. This program, supported by EIT Digital, a European institution that aims to create highly technical figures (in the robotics and AI fields) with also business knowledge applicable to the startup world. Highest possible exit grade (110 with honors out of 110).

Bachelor’s Degree in Information and Business Organization Engineering

University of Trento

Jan 2020 – Jun 2020 Trento (Italy)

Bachelor Degree focused on Computer Science, with topics like Object Oriented Programming (in C++), UML diagrams, database design and query with SQL, networking, Javascript development and Python development. A part of my study plan was also focused on business organization: I studied agile techniques for software development, process management and business strategy. Highest possible exit grade (110 with honors out of 110).

Publications

Simone Zamboni, Zekarias Tilahun Kefato, Sarunas Girdzijauskas, Christoffer Norén, LauraDal Col

January 2022 In Pattern Recognition

Pedestrian trajectory prediction with convolutional neural networks

Predicting the future trajectories of pedestrians is a challenging problem that has a range of application, from crowd surveillance to autonomous driving. In literature, methods to approach pedestrian trajectory prediction have evolved, transitioning from physics-based models to data-driven models based on recurrent neural networks. In this work, we propose a new approach to pedestrian trajectory prediction, with the introduction of a novel 2D convolutional model. This new model outperforms recurrent models, and it achieves state-of-the-art results on the ETH and TrajNet datasets. We also present an effective system to represent pedestrian positions and powerful data augmentation techniques, such as the addition of Gaussian noise and the use of random rotations, which can be applied to any model. As an additional exploratory analysis, we present experimental results on the inclusion of occupancy methods to model social information, which empirically show that these methods are ineffective in capturing social interaction.