# Daksh User

Daksh User is a remote worker on Himalayas, Undergraduate Thesis Research at IIT Roorkee, based in India.

Source: https://himalayas.app/@dakshuser3

```text
Undergraduate researcher at IIT Roorkee studying information leakage and safety trade-offs in multi-agent AI.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 140k+ INR |
| Job categories | Researcher |
| Skills | Multi Agent Systems, AI Safety, Information Theory, Decision Theory, Game Theory, Probability, Stochastic Process, Cryptanalysis, Post Quantum Cryptography, Side Channel Resistance, Homomorphic Encryption, LLM Evaluation, Information Flows, Mathematical Modeling, C++ |
| Website | https://da1729.github.io |

## What I'm looking for

```text
I’m interested in the mathematical foundations of multi-agent AI, especially how agents communicate, make decisions, and coordinate, and what can be established from observable behavior. I’m drawn to work on covert communication, monitoring limits, and safety–performance trade-offs.
```

## About

```text
At IIT Roorkee, in collaboration with COSIC, KU Leuven, I’m researching information flow, observational limits, and safety–performance trade-offs in LLM-based multi-agent systems. My work includes investigating how agents might retrieve sensitive information and coordinate communication, and comparing interaction protocols.

At COSIC, KU Leuven, I developed finite-model results on hidden information flow under passive monitoring and designed controlled sender–receiver experiments. I’ve also worked on post-quantum cryptography, including a memory-conscious ARM Cortex-M4 implementation of FAEST with Bocconi University, and write about mathematics, epistemology, logic, and intelligent systems.
```

## Experience

### Undergraduate Thesis Research (current)

[IIT Roorkee](https://himalayas.app/companies/indian-institute-of-technology-roorkee). Jan 2026 - Present

```text
Conducting research on mathematical foundations of LLM-based multi-agent systems, focusing on information flow, observational limitations, strategic coordination, and safety-performance trade-offs.
```

Skills: Multi-Agent-Systems, Information-Theory, Decision-Theory, Game-Theory, LLM-Security, Safety-Evaluation

### Research Intern

COSIC, KU Leuven. Jun 2026 - Aug 2026

```text
Independently explored LLM multi-agent security and formulated an information-theoretic investigation of passive monitoring limitations. Developed finite-model results and designed controlled LLM sender-receiver experiments.
```

Skills: LLM-Security, Information-Theory, Probability, Experimental-Design, Data-Analysis

### Undergraduate Researcher

Bocconi University. Jan 2026 - Apr 2026

```text
Worked on a memory-conscious ARM Cortex-M4 implementation of the FAEST post-quantum signature scheme, connecting cryptographic specifications to embedded memory and performance constraints.
```

Skills: ARM-Cortex-M, Post-Quantum-Cryptography, Embedded-Systems, C, Memory-Optimization

## Education

### Indian Institute of Technology Roorkee

B.Tech., Engineering Physics. 2023 - Present

Activities and societies: Mathematics: Real Analysis I–II, Linear Algebra, Number Theory, Graph Theory, Probability & Statistics, Complex Analysis, ODEs/PDEs, Fourier and Laplace methods, Mathematical Physics. Mathematical physics: Quantum Mechanics, Quantum Theory of Solids, Statistical Mechanics, General Relativity, Numerical Physics. Independent study: Abstract Algebra, Information Theory, Category Theory, Functional Analysis, Topology.

```text
Pursuing a B.Tech. in Engineering Physics with a minor in Mathematics and Computing, covering advanced mathematics and mathematical physics.
```

## Tech stack

- GitHub
- C++

To contact Daksh, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [R G](https://himalayas.app/@RajeetGhosh0): LLM Trainer, Turing
- [Ishu Dev](https://himalayas.app/@ishudev): Master's Researcher, National Institute of Technology, Rourkela
- [Aman Githala](https://himalayas.app/@amangithala): Information Theoretic Researcher, Faculty of Technology, University of Delhi
- [Kanishk Awadhiya](https://himalayas.app/@kanishkawadhiya): Quantitative Researcher, Stealth Startup
- [YASHASVI INDORA](https://himalayas.app/@yashasviindora): Undergraduate Researcher, Indraprastha Institute of Information Technology Delhi
- [Pritish Arora](https://himalayas.app/@pritisharora): Research Intern, DRDO Scientific Analysis Group
- [Diya M](https://himalayas.app/@diyam): Research Intern, IIT Kanpur
- [Niharika Verma](https://himalayas.app/@niharikaverma1): Junior Research Fellow, National Quantum Mission IIT Patna
- [Saptadip Saha](https://himalayas.app/@SaptadipSaha): Research Intern, Co creative Intelligence, JAIST
- [Namratha User](https://himalayas.app/@namrathauser): Teaching Assistant, Indian Institute of Science
