I don’t always test my code — but when I do, it’s in production.
🚀 I design, evaluate, and improve Large Language Model (LLM) systems with a focus on robustness, alignment, and real-world deployment.
🧠 Hands-on with RLHF, RAG, fine-tuning, and evaluation pipelines
⚙️ Built systems that improve model safety (60% → 99%) and reliability
🔬 Strong foundation in adversarial testing & failure analysis of LLMs
📦 Experience building end-to-end AI pipelines (data → model → evaluation)
💡 I specialize in turning research ideas into production-ready AI systems — building models that don’t just work, but work reliably under real-world conditions.
Feel free to contact me for collaboration 🤝, discussion 🤼 (haha couldn't find a better emoji XD) or for anything i could be helpful to you 😄
|
|
|
LLM & ML: RLHF (SFT, PPO, DPO) • RAG • Fine-tuning • PEFT (LoRA/QLoRA)
Frameworks: PyTorch • Hugging Face • LangChain • LlamaIndex
Languages: Python • C/C++ • JavaScript/TypeScript • SQL
Backend: Node.js • Express • REST APIs
Databases: MongoDB • PostgreSQL
Infra: Docker • Linux • SLURM
