Skip to content

Available for internships & new grad roles

Sudhan P.

Backend & AI-Security Engineer

CS undergrad at IIIT Sri City. I build backend systems that test, score, and defend AI — plus the occasional operating system.

See the workDownload résumé
sudhanp2004sudhan-psudhanp2004@gmail.com
01 / Work

Selected projects

AI Security2026

CASCADE — LLM Jailbreak Evaluation Framework

A Flask backend that runs multi-turn adversarial conversations against GPT, Claude, and Gemini, then scores how far each one bends.

PythonFlaskPortkeyLLM-as-Judge+2
AI Security2026

SOC Incident Response Agent — RL Benchmark

An OpenEnv-compliant environment that simulates a Security Operations Centre so LLM agents can be benchmarked on real incident-response tradeoffs.

PythonFastAPIOpenEnvMITRE ATT&CK+1
AI Security2025

AI-Powered Malware Detection

Real-time process surveillance that watches resource behaviour across running processes and flags anomalies with a Bidirectional LSTM.

PythonTensorFlowPyQt5Bi-LSTM+1
Data & Finance2025

Quantitative Strategy Backtester

A bar-by-bar backtesting engine over 100+ tickers that reports Sharpe, max drawdown, and the rest — without the CSV-and-for-loop tax.

PythonPandasNumPyParquet+2
AI & LLM2025

ULTRON — Natural Language to Linux

A backend layer that turns plain English into validated, executable Linux commands, grounded in documentation it scrapes itself.

PythonLangChainRAGVector DB+2

Also built

02 / Experience

Where I've worked

Ernst & Young (EY)

Jun 2026 — Present

SOC Intern — AI Security

  • Built and maintain an internal red-teaming service that automatically tests LLMs (GPT, Claude, Gemini) for jailbreaks and prompt injection before those models reach clients.
  • Wrote the Flask API and scoring pipeline behind it, integrating multiple provider APIs behind one interface so evaluation runs stay reproducible as the system scales.
  • Process and score large volumes of multi-turn conversation data, turning adversarial transcripts into metrics the security team can act on.
PythonFlaskLLM EvaluationRed Teaming

Education

  • Indian Institute of Information Technology, Sri City

    B.Tech, Computer Science and Engineering — CGPA 7.5

    Aug 2023 — Present · Sri City, AP

  • Expert PU College

    PCMC (Pre-University) — 91.66%

    Jun 2020 — Jun 2022 · Mangaluru, Karnataka

  • Amber Valley Residential School

    ICSE — 92.83%

    Jun 2015 — Apr 2020 · Chikmagaluru, Karnataka

Achievements

  • Finalist — Override.exe

    Ascent TechFest '26, Scaler School of Technology · May 2026

    Advanced through a competitive qualifier round to the finals of Scaler's annual Builders TechFest.

  • Runners-Up — HackTheThreat

    Abhisarga '25, IIIT Sri City · 2025

    Built an AI-based early malware detection system flagging malicious process behaviour through real-time resource monitoring. Also recognised as Trailblazer at IIIT Sri City.

03 / About

A bit more

I'm a Computer Science undergrad at IIIT Sri City and a SOC intern on the AI Security team at EY, where I build the red-teaming pipeline that stress-tests GPT, Claude, and Gemini for jailbreaks and prompt injection before those models reach clients.

Most of what I build lives on the backend: Flask and FastAPI services, data pipelines, evaluation harnesses, and scoring engines. The through-line is measurement — I like systems that turn a fuzzy question ("is this model safe?", "is this process malicious?", "does this strategy actually work?") into a number you can defend.

When I'm not doing that, I write x86 kernels from scratch and build desktop assistants that run fully offline.

Languages

PythonCJavaJavaScriptSQLHTML/CSS

Backend

FlaskFastAPINode.jsExpressREST API designReactRedux

AI & Security

LLM-as-judge evaluationJailbreak & prompt-injection testingMITRE ATT&CKRL environments (OpenEnv)RAG & vector searchThreat detection

Data

PandasNumPyETL pipelinesParquetWeb scrapingTensorFlow

Databases

MySQLMongoDBRedisVector DBsQuery optimisation

Tooling

Git/GitHubDockerAWSLinuxGitHub ActionsPostman
04 / Contact

Get in touch

I'm open to internships, new grad roles, and interesting problems in AI security, backend, or anything close to the metal. The fastest way to reach me is email.

Emailsudhanp2004@gmail.comGitHubsudhanp2004LinkedInsudhan-p