A short version.
I'm currently a research fellow at the Cooperative AI Research Fellowship in Cape Town, working on multi-agent systems. I just finished my B.Tech in CS at Heritage Institute of Technology, Kolkata. The rest below: origin, the work, and the path through the roles.
Origin
I grew up in Kolkata. First person in my family to work in science. Got reliable internet in 2019. Most of what I know I picked up on the way, partly because I had to, partly because I kept getting curious about the next thing.
My research career came together through hackathons, open source, and small projects. I still don't consider myself an expert. I just tried a bunch of things, and a few of my bets worked out.
Outside research
Bengali music, mostly Anupam Roy. Beatboxing. Guitar. A 5,000-piece Creation of Adam on the floor that I keep meaning to finish. And a daily video log I've been making to stay honest about what the work actually feels like.
Trajectory
- Research Fellow Cooperative AI Research Fellowship
- 1 of 10 fellows from a global pool of 1,000+ applicants (<1% acceptance). Mentored by Prof. Vincent Conitzer.
- Empirical research on multi-agent risks and the foundations of cooperative game theory.
- Talks at Stellenbosch University and the University of Cape Town. 1 of 2 fellows selected for the funded extension through August.
- Research Collaborator FAR AI
- Building a toolkit that empowers expert frontier-model red-teaming.
- Data Scientist Humane Intelligence
- Red Teaming Evaluations team: analysed post-event red-teaming data and prepared comprehensive reports.
- Built an Auto-Red-Teaming LLM that autonomously generates exploit-style prompts for multilingual and sociocultural safety, using LoRA fine-tuning and causal LM training.
- Core contributor to the Singapore AI Safety Red Teaming Challenge (with the Singapore government, IMDA).
- Research Fellow Apart Research
- Cross-lingual capabilities of safety evaluation benchmarks.
- Co-authored the DarkBench dataset (600+ adversarial prompts across six dark-pattern categories), accepted as an ICLR 2025 Oral.
- Research Intern Lionheart Ventures
- Built a framework to evaluate AI-induced systemic risks across 10+ portfolio companies.
- Cluster analysis over 600+ distinct AI-related threats; Monte Carlo risk-weighting in the style of MIT's AI Risk Initiative.
- Integrated into internal due-diligence for funding evaluations.
Invited talks
-
Getting Into AI Safety Research: Opportunities and Pathways
-
Dark Patterns in Large Language Models
-
Similarity as a Signal: Do AI Agents Cooperate More When They Know They're Alike?
-
Similarity as a Signal: Do AI Agents Cooperate More When They Know They're Alike?
-
Similarity as a Signal: Do AI Agents Cooperate More When They Know They're Alike?
Professional service
-
Organizing Committee & Reviewer
Reviewer recruitment, desk-rejection screening, and reviewing submissions on alignment faking and multi-agent cooperation.
-
Judge
-
Reviewer
Volunteering & teaching
- AI/ML Lead · Tech Lead Google Developer Student Clubs
- Led the club's technical domain (14 domain mentors across web, Android, and ML) for a community of 1,800+ active members.
- Designed and led hands-on ML coding sessions with 150+ participants. Launched the institute's first ML Hackathon (300+ participants).
- Volunteer ML Engineer Omdena
- Deepfake detection for women's safety (Germany).
- Out-of-pocket lung-cancer cost estimation, ±10% CI (US).
- Personality-based hostel roommate matching (Egypt).
- Vicuna-13B mental-health chatbot for Tanzania (English + Swahili).
Things I've won / been picked for
-
Accepted: Cooperative AI Summer School
-
Recipient: $1,000 Travel Grant
-
1st of 3,000: Kaggle Data Science Hackathon
-
1st: NeurIPS Concordia Hackathon
$1,100 in Google DeepMind researcher credits · invited to present at the NeurIPS 2024 Concordia Workshop
-
Winner: Spectral Syntax Bounty, Web3 × AI Hackathon
$2,000
-
Winner: LLM Evaluations Hackathon + AI Security Evaluations Hackathon
-
Winner: MLTiverse
-
1st Runner-up: ClimateConnect Hackathon
-
Accepted: CaMLAB V4
-
Shortlisted (Round 3): Atlas Fellowship India
-
Past Fellow: Whitebox Research
-
Past Fellow: Supervised Program for Alignment Research
Certifications
-
AI Safety Fundamentals: Alignment Course
Weekly discussions on alignment research and technical AI safety. Built the Werewolf Benchmark, a project highlighting the deceptive capabilities of LLMs.
-
Introduction to Cooperative AI
Education
B.Tech, Computer Science and Engineering
GPA 8.75 / 10 · final year 9.33 / 10
Get in touch.
The easiest way is email: akashkundu2xx4@gmail.com. I'm also around in the usual places: