I work at the intersection of Applied AI and security engineering — red teaming and building controls for production AI systems at my workplace before they reach end users. Traditional security reviews don't cut it for AI. My job is to find the things that change deployment decisions.
What I'm working on:
- Engineered a firm-wide Gen AI Red Teaming platform enabling systematic automated and manual adversarial evaluation of LLM use cases across all lines of business
- Led the red team assessment of flagship LLMs, surfacing multiple critical and high-severity vulnerabilities — prompt injection, data leakage, system prompt extraction, and intent drift — before the models reached production
- Authored a blueprint for Advanced Manual Red Teaming: a structured methodology for uncovering behavioral vulnerabilities and intent misalignment that automated scanners fundamentally cannot detect
- Architected a Network Broker enabling secure, isolated connectivity between internal red teaming platform and external vendor evaluation infrastructure
- Containerized and deployed Red Teaming ECS Task modules for concurrent adversarial evaluation of multiple AI use cases without capacity constraints
- Reviewed emerging AI coding tools from a security perspective, producing key findings that directly shaped firm-wide decisions on AI coding enablement
- Building AI Controls engineering solutions to systematically enforce safety, scope, and behavioural boundaries across deployed LLM use cases
Recognition: Inventor Recognition (Q4 2025) for filed patents · Speaker at DEVUP 2026 (my workplace's invite-only technical conference) · SEP Engineer Committee Lead for 1,100+ early-career engineers at my workplace Bengaluru Tech Centre
Full-fledged engineering projects: red-teaming tools, safety benchmarks, and taxonomies built to address real gaps in how deployed LLMs are secured.
Interactive AI Security Hacking Playground
A gamified Capture The Flag platform designed to teach hands-on adversarial thinking. Mapped directly to real-world risk frameworks (OWASP LLM Top 10 & MITRE ATLAS).
- 5 Progressive Levels covering basic injection, jailbreaks, intent drift, token smuggling, and multi-vector chaining
- Zero-API-cost heuristics engine (Base64, roleplay markers) for instant feedback
Prompt Injection Benchmark for Agentic Tool-Use
The first benchmark targeting injection attacks in agentic, tool-using pipelines — tool-output injection and goal hijacking across multi-step workflows, where single-turn benchmarks like AdvBench and HarmBench don't reach.
- Covers Tool Output Injection, Goal Hijacking, and multi-step attack chains
- Dataset & interactive Space published on Hugging Face
Absolute Safety Robustness Evaluation Harness
An advanced LLM safety benchmark that evaluates absolute, severity-weighted category failure rates instead of shifting, relative statistics (Z-scores).
- Built on top of the UK AISI's open-source inspect_ai framework
- Risk-adjusted severity weighting: prompt injection (0.3), jailbreaks (0.3), data exfiltration (0.2), toxicity (0.1), malware (0.1)
Multi-Turn Jailbreak Taxonomy & Detection
A taxonomy of trajectory-based LLM jailbreak patterns — gradual drift, persona anchoring, trust escalation — that single-turn automated scanners structurally can't catch, plus concrete detection methods.
- 9 named attack patterns, each grounded in cited research (Crescendo, Anthropic's many-shot jailbreaking)
- Practical detection section: embedding-based drift scoring, trajectory-level judge scoring, tooling landscape
AI Scope & Intent Enforcement Proxy Gateway
An enterprise-grade safety proxy and automated red-teaming tool designed to keep deployed LLM applications safe, secure, and strictly aligned within their defined scopes.
- IntentScan: Automated red-teaming simulating Role Transformation, Gradual Drift, and Language Variation attacks
- IntentEnforce: Runtime reverse proxy utilizing LLM classification allow/block policies
🔒 Stealth / Private Repository
The Definitive AI Security Practitioner's Guide
A curated, practitioner-depth guide to AI red teaming, runtime security, and MLSecOps — 14 specialized handbooks, not a link dump.
- Deep-dive handbooks: manual red teaming, standards & compliance, benchmarks, 2026 incidents & CVEs
- Zero-to-Hero 12-month curriculum + hands-on labs (FGSM, prompt injection, RAG hijacking)
AgentInjectionBench (⭐ 2) — The first benchmark targeting prompt injection attacks in agentic tool-use pipelines — tool output injection, goal hijacking, and multi-step attack chains. Dataset & Space on Hugging Face.
ai-security-resources (⭐ 2) — Curated directory of state-of-the-art Adversarial AI Security tools, vulnerability scanners, safety benchmarks, guardrails, and compliance standards.
prompt-injection-ctf (⭐ 2) — Interactive AI Security Playground — Prompt Injection CTF. Craft attack prompts to break constrained AI systems. Learn prompt injection, jailbreaking, intent drift & token smuggling. Built to teach adversarial thinking hands-on.
weighted-safety-refusal (⭐ 1) — Severity-weighted LLM safety evaluation suite. Measures absolute refusal robustness across prompt injection, jailbreaking, data exfiltration, toxicity, and malware generation using risk-adjusted weights.
synaptic-wetware — 🧠 Organoid Intelligence Biocomputer Simulator — HH + Izhikevich neuron models, MEA burst detection, DishBrain Pong, Baltimore Declaration ethics monitor. Built by Antigravity (Google DeepMind).
intent-drift-playbook — A taxonomy of trajectory-based LLM jailbreak patterns (gradual drift, persona anchoring, trust escalation) that single-turn automated scanners structurally can't catch — plus concrete detection methods.
ai-security-tracker — Real-time security monitoring across 50+ AI/ML repositories — tracks vulnerabilities, CVEs, and security initiatives ecosystem-wide.
llm-ops-workshop — End-to-end MLOps workflow demonstrating model lifecycle, monitoring, and deployment practices.
Also building something in AI security — stealth mode 🔒
📋 Full list of external contributions — repos outside my account where I've contributed (2020–present)
LLMs & AI Platforms
Claude ChatGPT Gemini Grok Llama Mistral Copilot NVIDIA NIM Hugging Face
Red Team & Security Tools
Garak PyRIT Promptfoo Protect AI Prisma AIRS NeMo Guardrails Lakera Guard Burp Suite Counterfit
Frameworks & Standards
OWASP LLM Top 10 MITRE ATLAS NIST AI RMF
ppradyoth ppradyoth @ppradyoth ppradyoth ppradyoth @ppradyoth pradyothp ppradyoth ppradyoth
Tech Stack
python java spring docker kubernetes aws terraform kafka redis mysql grafana jenkins linux git postman raspberrypi c cplusplus css3 html5 javascript go nodejs mongodb firebase gcp heroku opencv pandas scikit_learn tensorflow tailwind photoshop