# Ayush Kumar

Ayush Kumar is a remote worker on Himalayas, Software Development Intern at Carboledger, based in India.

Source: https://himalayas.app/@ayushkumar912

```text
Software engineer-intern and LLM security researcher building secure, scalable backend systems.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 900k-1500k INR |
| Job categories | Software Engineer, Backend Engineer |
| Skills | C C++, Python, JavaScript, SQL, Node.Js Development, Express, fastAPI, Flask, Prisma, PostgreSQL, MongoDB, MySQL, Redis, Docker, Git, Postman, Swagger, Selenium, Jira, TensorFlow, OpenCV, scikit learn, Prompt Injection, LLM Security Testing, Responsible Disclosure, Helmet.Js, XSS, RESTful API Design, NodeJS, GitHub, Middleware |
| Website | https://ayushkumar912.pages.dev |
| LinkedIn | https://https://www.linkedin.com/in/ayushkumar912/ |
| GitHub | https://https://github.com/ayushkumar912 |

## What I'm looking for

```text
I’m looking for a role where I can build secure, scalable backend/web systems and apply LLM security research—owning bugs, improving latency, and shipping reliable features in a fast, collaborative team.
```

## About

```text
I’m a software engineer-intern and independent LLM security researcher focused on building reliable backend systems and improving real-world security. I enjoy turning requirements into production-ready features, designing modular components, and raising system quality through careful debugging and testing.

At Carboledger, I worked on a multi-tenant compliance platform with complex domain workflows. I merged 65 PRs in 16 weeks, converted requirement cards into extensible backend features using design patterns and modular architecture, and owned critical bug identification and resolution across cross-version testing and regression cycles.

Earlier, at Fast Conversion eSolutions Private Limited, I improved web performance and API efficiency as a Web Development Intern. I reduced API latency using Redis session caching and async Express middleware, then refactored 12 REST endpoints to eliminate N+1 queries and add connection pooling—cutting down average database query time.

I also pursue security research through independent LLM security work. I identified and responsibly disclosed a critical prompt leakage vulnerability in a Claude-based code review platform (CodeVerdict), providing root cause, reproduction steps, and actionable remediation; I was recognized for report quality and security depth. In parallel, I build ML/CV solutions like a CDM-based fake image detection pipeline and a Flask-based toddler autism prediction API achieving strong evaluation results, guided by careful end-to-end experimentation.
```

## Experience

### Software Development Intern

Carboledger. Jan 2026 - May 2026

```text
Merged 65 PRs over 16 weeks on a multi-tenant compliance platform, converting requirements into production-ready backend features. Owned critical bug identification and resolution to improve workflow accuracy and system reliability across testing and regression cycles.
```

Skills: Design-Patterns, Backend-Development, Frontend-Development, Bug-Resolution, Regression-Testing

### Web Development Intern

Fast Conversion ESolutions Private Limited. Mar 2024 - Jun 2024

```text
Reduced API latency using Redis session caching and lazy-loaded non-critical Express middleware. Refactored REST endpoints to eliminate N+1 queries and implement connection pooling, improving database query performance.
```

Skills: Redis, Express, Asynchronous-Programming, Connection-Pooling, N+1-Query-Elimination

### LLM Security Research

CodeVerdict. Jun 2026 - Present

```text
Identified and responsibly disclosed a critical system prompt leakage vulnerability affecting CodeVerdict’s Claude-based code review platform. Conducted adversarial input testing against LLM context-boundary trust assumptions and produced a high-quality security report.
```

Skills: LLM-Security-Testing, Vulnerability-Research

## Education

### Stanford University

Machine Learning Specialization, Machine Learning. Grade: 98%

```text
Completed the Machine Learning Specialization (Stanford University & DeepLearning.AI) with a 98% grade, covering supervised, unsupervised, and deep learning.
```

### Indian Institute of Information Technology, Vadodara

Bachelor of Technology, Computer Science and Engineering. 2022 - 2026. Grade: 7.2/10

Activities and societies: Relevant coursework: Data Structures, Algorithms, Database Systems, Operating Systems, Artificial Intelligence, Machine Learning, Cyber Security and Cryptography.

```text
Pursuing a Bachelor of Technology in Computer Science and Engineering at IIIT Vadodara (2022–2026), with coursework in data structures, algorithms, databases, operating systems, AI/ML, and cyber security/cryptography.
```

### Atlassian

Atlassian Agile Project Management Professional Certificate, Agile Project Management

```text
Gained expertise through the Atlassian Agile Project Management Professional Certificate, covering Scrum practices such as backlog grooming, sprint planning, and Jira workflows.
```

## Tech stack

- Postman
- GitHub
- MySQL
- PostgreSQL
- MongoDB
- Node.js
- OpenCV
- Redis
- Jira
- JavaScript
- TensorFlow
- scikit-learn
- FastAPI
- Prisma
- SQL
- Middleware

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

## People also viewed

- [Yashas Shetty](https://himalayas.app/@yashasshetty): Backend Developer, WOWR
- [Soham Vaghela](https://himalayas.app/@sohamvaghela): Machine Learning Intern, Groovy Web
- [harshita roonwal](https://himalayas.app/@harshitaroonwal1): Software Developer Intern, Rippling
- [Mimansa Sahay User](https://himalayas.app/@mimansasahayuser): Backend Development Intern, Episodic Labs
- [Tejas Ghoti](https://himalayas.app/@tejasghoti): AI Full Stack Engineering Intern, NeuraMach.AI
- [sai teja](https://himalayas.app/@saiteja16): Software Engineering Intern, Aude.ai
- [Akshat Mathur](https://himalayas.app/@akshatmathur2): Software Engineering Intern, Outcom.AI
- [Aryan Ghai](https://himalayas.app/@aryanghai1): Independent Security Researcher, HackerOne
- [Ishaan Goswami](https://himalayas.app/@ishaangoswami): SDE Intern, LawBot Express
- [Diptesh Narendra](https://himalayas.app/@dipteshnarendra): Cybersecurity Intern, YHILS (Remark Skill Education)
