s
sidharth1

Sidharth P

@sidharth1

AI Safety Researcher and LLM Fine Tuning Expert

Índia
Telugu
Algumas informações são exibidas no idioma inglês.
Sobre mim
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.... Saiba mais

Habilidades

s
sidharth1
Sidharth P
offline • 

Conheça meus serviços

Implementação e Implantação de IA
I will fine tune llama, qwen or mistral llms on your data with lora
A partir deUS$ 30 /projetoMais detalhes
Consultoria de Tecnologia de IA
I will red team your llm agent for prompt injection and memory attacks
A partir deUS$ 25 /projetoMais detalhes

Portfólio

Experiência profissional

SPAR

Research Fellow

SPAR

Sep 2025 - Sep 2026 • 1 yr

AI safety research fellowship (SPAR, Supervised Program for Alignment Research) focused on the security of LLM agents with long-term memory: how agent memory can be poisoned and how attacks can spread between agents that share memory. Related work: "Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents" and "Hidden in Memory: Sleeper Memory Poisoning in LLM Agents" (arXiv, 2026).