AI software engineer specializing in LLM inference optimization⚡with over 2 years of experience at Intel 🏢. Core focus areas include: 1) architecting model compression algorithms (sparsity, pruning, quantization) to overcome compute and memory bottlenecks, and 2) designing efficient heterogeneous (GPU-CPU) inference framework and KV-cache management mechanism for agentic AI workloads. Published 5+ papers in AI conferences (EMNLP, NAACL, NeurIPS), holding 1 US patent, with 150+ citations. Dedicated to delivering lightweight, efficient algorithmic solutions for research and deployment, and bridging the gap between high-level algorithmic research and low-level system efficiency.

Interests 🚩

• Natural language processing (NLP), large language models (LLM).
• Model inference acceleration, model compression (sparsity/pruning/quantization), neural architecture search (NAS).
• LLM fine-tuning, parameter-efficient fine-tuning (PEFT), LoRA.
• LLM serving engine, heterogeneous inference (GPU-CPU), KV-cache management and scheduling, agent memory management, agentic AI.
• Retrieval-augmented generation (RAG), test-time compute.

I am always open to discussions and potential collaborations. Please feel free to reach out! 🤝

Experience 💼

• System Software Development Engineer @ Intel
  Jul. 2023 - Mar. 2026 (2 yrs 9 mos) · Beijing, China

• System Software Development Engineer (Intern) @ Intel
  May 2022 - Jun. 2023 (1 yr 2 mos) · Beijing, China

• M.S. in Computer Science and Technology @ Guangdong University of Technology
  Sep. 2020 - Jun. 2023 · Guangzhou, China
  Recommended for Admission without Examination
  _Prof. Ruichu Cai @ DMIR Lab

• B.S. in Software Engineering @ Guangdong University of Technology
  Sep. 2016 - Jun. 2020 · Guangzhou, China

Selected Publications 📚

For a full list, please refer to my Google Scholar.

• RTTC: Reward-Guided Collaborative Test-Time Compute
  J. Pablo Muñoz*, Jinjie Yuan* (Co-first author)
  EMNLP 2025 Findings · Paper

• Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models
  J. Pablo Muñoz*, Jinjie Yuan* (Co-first author), Nilesh Jain
  NAACL 2025 (Oral) · Paper · Code

• Low-Rank Adapters Meet Neural Architecture Search for LLM Compression
  J. Pablo Muñoz, Jinjie Yuan, Nilesh Jain
  AAAI 2025 Workshop · Paper

• SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models
  J. Pablo Muñoz*, Jinjie Yuan* (Co-first author), Nilesh Jain
  EMNLP 2024 Findings · Paper · Code

• Shears: Unstructured Sparsity with Neural Low-rank Adapter Search
  J. Pablo Muñoz*, Jinjie Yuan* (Co-first author), Nilesh Jain
  NAACL 2024 · Paper · Code

• LoNAS: Elastic Low-rank Adapters for Efficient Large Language Models
  J. Pablo Muñoz*, Jinjie Yuan* (Co-first author), Yi Zheng, Nilesh Jain
  LREC-COLING 2024 · Paper · Code

• SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
  Ruichu Cai, Jinjie Yuan (First student author), Boyan Xu, Zhifeng Hao
  NeurIPS 2021 · Paper · Code

Patents 📝

• Methods and apparatus for enabling efficient fine-tuning on unstructured sparse and low-precision large pre-trained foundation models
  J. Pablo Muñoz, Jinjie Yuan, Nilesh Jain
  US Patent App. 18/935,223 (2025)