01
AI Developer Tools
Next-generation code analysis utilities and static checkers wired into reasoning models.
Available for workbenzo
>
I build products at the intersection of AI, security, and developer tooling — fast software, hard engineering problems, and a standing habit of breaking things in CTFs.
- Focus
- AI × Security
- Writing
- Systems deep-dives
- Playing
- CTFs, weekly
01 / About
Hi, I am Tushar 👋
I focus on building and breaking complex systems. As a Software Engineer, I design robust architectures ranging from minimal, highly-responsive user interfaces to scalable backends. My primary AI research and engineering efforts are concentrated around AI Systems, LLM Agents, RAG pipelines, and Multi-Agent Orchestrations.
On the security front, I research Web App Security, Cloud Security, and offensive operations. Balancing full-stack engineering and security audits lets me build applications that are high-fidelity, high-performance, and resilient against modern attack layers.
~ $whoami
tushar — a.k.a 0xbenzo
~ $cat role.txt
software engineer · security researcher
~ $ls interests/
ai-systems appsec distributed devtools
~ $uptime
shipping, breaking, writing — daily
~ $
02 / Focus
What I'm working on
Six threads I'm pulling on right now — where engineering, AI, and offensive security overlap.
02
Agentic Systems
Safe state machines and routing graphs for multi-agent loops that never fall into looping traps.
03
Security Research
Auditing application dependencies and mapping novel injection paths across distributed networks.
04
Competing in CTFs
Solving high-difficulty challenges and engineering attack/defense targets for competitive arenas.
05
Indie Product Dev
Shipping minimal, high-utility tools for developer problems on short iteration cycles.
06
Technical Writing
Deep-dives on systems architecture, security remediation, and performance work.
03 / Selected work
All projectsFeatured Projects
Production tools, experimental architectures, and security utilities I've shipped.
P/01active
EHAX CTF Platform
A highly resilient, containerized cybersecurity capture-the-flag platform designed to handle thousands of concurrent players.
GoReactDockerRedisPostgreSQL
P/02active
AgentScan AI
An automated static analysis scanner that identifies indirect prompt injections and unsafe tool definitions inside LangGraph systems.
PythonLangGraphFastAPITypeScriptAnthropic
04 / Writing
All articlesLatest Articles
Notes from the systems I build, break, and benchmark.
Understanding std::unordered_map Internals: How Hash Tables Really Work
A deep dive into the inner workings of C++ std::unordered_map, exploring hash functions, bucket allocation, separate chaining, load factors, and rehashing.
Building a Minimal gRPC Server and Client in Go
Learn how to build your first gRPC application in Go by creating a simple server and client that communicate using Protocol Buffers.
Understanding gRPC & Protocol Buffers
Learn what gRPC and Protocol Buffers are, how they work together, and why they have become the preferred communication technology for modern microservices and cloud-native applications.
Suricata: A Complete Guide to Modern Network Threat Detection
A comprehensive guide to Suricata, its architecture, rules, deployment modes, and integration with modern SIEM platforms.
vLLM: A Modern Inference Engine for Large Language Models
An exploration of how vLLM serving is optimized using Continuous Batching and PagedAttention.
05 / Stack
Tools of the trade
The languages, runtimes, and platforms I reach for most.
Languages
PythonGoTypeScriptJavaScriptRust (learning)
Backend
Node.jsExpressFastAPI
Databases
PostgreSQLMongoDBRedis
DevOps
DockerGitHub ActionsLinuxCloudflareAWS
AI Systems
LangGraphOpenAI APIAnthropic APIVector DatabasesRAG
Cybersecurity
Burp SuiteSplunkNmapOWASPCTFs