Large Language Models • Autonomous Agents • Applied AI Systems

Building production-grade LLM-powered agents, reasoning systems, and evaluation frameworks.

• Fine-tuning & alignment of open-source LLMs (Llama 3, Mistral, Qwen, etc.)
• Agent architectures: ReAct, Tool-use, Multi-agent systems, Long-context reasoning
• RAG pipelines, vector stores, retrieval evaluation, and context optimization
• LLM evaluation (MT-Bench, Arena-Hard, custom reasoning benchmarks)
• Inference optimization (vLLM, TensorRT-LLM, quantization-aware training)

I ship LLM/agent experiments every day on youtube.com/@museltabares

DMs on discord: m0285_