>

Arka Mitra

ETH Zürich Graduate | Swiss B Permit | ML Engineer & Software Developer — Ready to build amazing things

Download CV Contact Me

About Me

I'm an ETH Zürich graduate with a Swiss B permit and immediate availability for engineering roles. With experience spanning NLP, Computer Vision, and Software Engineering, I've built production-grade systems that serve thousands of users daily. My background includes optimizing LLM latency by 65%, developing multi-sensor fusion pipelines for robotics, and creating full-stack applications for financial analytics.

Whether it's reducing query latency from 3.4s to 1.2s, building automated trading systems, or teaching robots to play soccer—I love solving complex technical challenges. I bring both theoretical depth from my ETH education and practical experience from industry roles at Microsoft, Telepathy Labs, and leading technical teams. Ready to contribute from day one with proven skills in Python, C++, PyTorch, and modern MLOps practices. (Tip: There might be specialized versions of this profile floating around the internet... 🤫)

Email Scholar Twitter GitHub LinkedIn
Arka Mitra

Latest News

Optimizing Long-Term Player Tracking and Identification in NAO Robot Soccer by fusing Game-state and External Video was accepted in ICRA 2023.

NomadZ visited Hamburg for GORE 2023.

Received grants from NCCR Automation and KIM for NomadZ.

Causality Detection using Multiple Annotation Decisions was accepted to EMNLP 2022.

One of the finalists at HackZurich 2022.

NomadZ visited Bangkok for RoboCup 2022.

Helped organize Medical Imaging using Deep Learning conference 2022.

Joined the computer vision group of NomadZ.

Publications

I'm interested in computer vision, deep learning, image processing and natural language processing. Some papers are listed below.

ICRA 2023 Paper

Optimizing Long-Term Player Tracking and Identification in NAO Robot Soccer by fusing Game-state and External Video

Giuliano Albanese*, Arka Mitra*, Jan-Nico Zaech*, Yupeng Zhao*, Ajad Chhatkuli, Luc Van Gool

International Conference on Robotics and Automation, 2023

We propose an approach for long term tracking of similar looking Nao Robots using quadratic optimization which combines the robot's internal states and video from non-calibrated camera.

Paper
Referee Dataset

Multi-Domain Referee Dataset: Enabling Recognition of Referee Signals on Robotic Platforms

Arka Mitra*, Lukas Molnar, Jan-Nico Zaech, Yan Wu, Seonyeong Heo, Fischer Yu, Luc Van Gool

RoboLetics: Workshop on Robot Learning in Athletics@ CoRL, 2023

We introduce a dataset consisting of both synthetic and real-world referee signals. Additionally we show the amount of data required to train an end-to-end model using real data if already trained on synthetic data.

Paper
EMNLP Paper

Causality Detection using Multiple Annotation Decisions

Quynh Anh Nguyen*, Arka Mitra*

Empirical Methods in Natural Language Processing, 2022

We propose a loss which considers the decision from multiple different annotators for causality detection.

Paper
Hate Speech Detection

Multilingual Hate Speech and Offensive Content Detection using Modified Cross-entropy Loss

Arka Mitra*, Priyanshu Sankhala*

Forum for Information Retrieval, 2021

We create a model for hate speech and offensive content detection in multiple languages.

Paper
Rheumatoid Arthritis Detection

Quantum-Inspired Interpretable AI-Empowered Decision Support System for Detection of Early-Stage Rheumatoid Arthritis in Primary Care

Samira Abbasgholizadeh Rahimi, Mojtaba Kolahdoozi, Arka Mitra, Jose L. Salmeron, Amir Mohammad Navali, Alireza Sadeghpour, Seyed Amir Mir Mohammadi

Mathematics Journal, 2022

We detect early-stage Rheumatoid Arthritis using meta-heuristic search, combining it with fuzzy logic to provide explainable feature importance.

Paper
COVID Detection

Automated COVID-19 Detection from CT Images Using Deep Learning

Abdulhamit Subasi, Arka Mitra, Fatih Ozyurt, Turker Tuncer

Book Chapter in Computer-aided Design and Diagnosis Methods for Biomedical Applications, 2021

We show a comparison of classical and deep learning based methods for detecting COVID-19 from CT images.

Paper
Drone Detection

Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge

Angelo Coluccia, Alessio Fascista, Arne Schumann, Lars Sommer, Anastasios Dimou, Dimitrios Zarpalas, Miguel Méndez, David de la Iglesia, Iago González, Jean-Philippe Mercier, Guillaume Gagné, Arka Mitra, Shobha Rajashekar

Sensors Journal, 2021

We evaluated different deep learning models and techniques for tracking drones in videos. It was done as a part of my internship at Honeywell.

Paper
Chemistry CNN

Determination of stable structure of a cluster using convolutional neural network and particle swarm optimization

Arka Mitra, Gourhari Jana, Ranita Pal, Pratiksha Gaikwad, Shamil Sural, Pratim Kumar Chattaraj

Theoretical Chemistry Accounts, 2021

We combine machine learning methods with meta-heuristic optimization to speed up the convergence of stable cluster structures.

Paper
IIT KGP

IIT kgp at FinCausal 2020, Shared Task 1: Causality Detection using Sentence Embeddings in Financial Reports

Arka Mitra*, Harshvardhan Srivastava*, Yugam Tiwari*

COLING: International Conference on Computational Linguistics, 2020

We demonstrate that embeddings from large language models can be used to detect causality in a sentence. Additionally, we show that models trained on next sentence prediction are better in predicting causality.

Paper
X-ray Analysis

A Systematic Search over Deep Convolutional Neural Network Architectures for Screening Chest Radiographs

Arka Mitra*, Arunava Chakravarty*, Nirmalya Ghosh, Tandra Sarkar, Ramanathan Sethuraman, Debdoot Sheet

EMBC: IEEE Engineering in Medicine and Biology Conference, 2020

We explain the predictions of deep learning models on chest x-rays. The results were validated by a radiologist.

Paper
Chemistry Flat

Integrating firefly algorithm with density functional theory for global optimization of Al42− clusters

Arka Mitra, Gourhari Jana, Prachi Agarwal, Shamil Sural, Pratim Kumar Chattaraj

Theoretical Chemistry Accounts, 2019

We incorporate domain knowledge into meta-heuristic algorithms to improve the convergence of the algorithms.

Paper
Carbon Chemistry

Modified Particle Swarm Optimization Algorithm for Global Optimization of Carbon Clusters

Gourhari Jana, Arka Mitra, Sudip Pan, Shamik Sural, Pratim Kumar Chattaraj

Frontiers In Chemistry, 2019

We find the most stable structures of carbon clusters using a meta-heuristic algorithm in combination with Gaussian07 software.

Paper
View All Publications on Google Scholar

Projects & Blog

A collection of research projects and technical insights I've been working on.

Untangling ML Blog

Untangling ML

I keep track of some of the machine learning papers and provide insights on latest research developments.

Visit Blog

NomadZ

Robot Soccer Computer Vision

Leading computer vision efforts for NomadZ robosoccer team at ETH Zurich, teaching robots to play soccer autonomously.

Computer Vision Robotics Deep Learning

Research

ML Research Projects

Various research projects in computer vision, NLP, and deep learning including causality detection, medical imaging, and optimization algorithms.

NLP Medical AI Optimization

Skills & Expertise

Programming

Python C++ MATLAB JavaScript SQL

ML/AI

PyTorch TensorFlow Computer Vision NLP Deep Learning

Tools & Platforms

Git Docker AWS Linux Jupyter

Let's Connect

I'm always open to discussing new opportunities, research collaborations, or interesting projects in machine learning and computer vision.

Send Email LinkedIn