I will red team your llm agent for prompt injection and memory attacks

S
sidharth1
S
sidharth1
Sidharth P

About this gig

Is your LLM agent safe to put in front of real users? I will attack it the way a real adversary would and tell you exactly what breaks and how to fix it.


I am an AI safety researcher with papers at ICML and IJCNLP and arXiv work on memory attacks against LLM agents. I have also built LLM-judge evaluation benchmarks, so my testing is systematic and reproducible, not a handful of clever prompts.


What I test:

  • Prompt injection (direct and via documents, web pages or tool outputs)
  • Jailbreaks and policy bypass
  • Tool and function-call misuse
  • Memory and context poisoning in agents with long-term memory
  • System prompt and data leakage


What you get:

A clear written report with each finding, a reproducible example, a severity rating and a concrete fix. Higher packages add the attack suite as code so you can rerun it, plus a retest after you patch.


Works with OpenAI, Anthropic, open-source models, LangChain, LlamaIndex and custom agent stacks. Message me first with a short description of your agent and I will confirm scope. I only test systems you own or are authorized to test.

Get to know Sidharth P

Sidharth P

AI Safety Researcher and LLM Fine Tuning Expert

  • FromIndia
  • Member sinceApr 2017
  • Languages

    Telugu, English, Hindi
AI researcher in LLM safety and NLP. Research Intern at AI4Bharat (first author of IndicBERT-v3, open multilingual encoder LLMs) and Research Fellow at SPAR. Papers at ICML 2026 and IJCNLP-AACL 2025, plus arXiv work on memory attacks against LLM agents. Hands-on with LoRA/QLoRA and full fine-tuning (SFT, GRPO), multi-GPU training on H100s, vLLM/SGLang inference and LLM-as-judge evaluation. I help teams fine-tune open-source LLMs, build evaluation pipelines, red-team LLM agents and reproduce ML papers. Message me your goal and I will reply with a clear plan.

My Portfolio

Other AI Development Services I Offer

Related tags