My AI Portfolio

Engineering advanced AI systems—from autonomous multi-agent systems and scaling reasoning-focused LLMs on multi-node GPU clusters to performance profiling and distilling DeepSeek R1.

• AI Agent
• LLM Benchmarking and Profiling
• LLM Distillation & Fine-Tuning
• Generative AI & Applied Machine Learning

---

AI Agent

Building intelligent AI agents that dynamically reason, retrieve, and self-correct—from Agentic RAG with colocated vLLM inference to tool-augmented reasoning on the GAIA benchmark.

Key projects:

• Agentic RAG — Agent-based retrieval with iterative query refinement, achieving superior accuracy over Standard RAG and standalone LLMs. Details →
• Colocated vLLM Inference — Zero-egress, GPU-cluster deployment with a three-phase hybrid pipeline that collapses latency by an order of magnitude. Details →
• AI Multi-Agent Orchestration — Hierarchical smolagents framework with Langfuse telemetry; achieves 80% accuracy on GAIA benchmark, outperforming GPT-4’s 14.4% baseline. Details →

Explore all AI Agent projects →

---

LLM Benchmarking and Profiling

Systematic performance analysis of Transformer architectures—benchmarking FP32 vs. BF16 mixed precision and profiling compute- vs. memory-bound operations in self-attention.

Key projects:

• FP32 vs. BF16 Benchmarking — BF16 mixed precision delivers up to 6× inference throughput and unlocks training of larger architectures that fail under FP32. Details →
• Arithmetic Intensity Profiling — Reveals why MatMul completes in half the time of Softmax despite 25.6× more FLOPs, demonstrating the compute-bound vs. memory-bound paradigm. Details →

Explore all Benchmarking projects →

---

LLM Distillation & Fine-Tuning

Advanced post-training and fine-tuning across large language models—from distilling DeepSeek R1 on multi-node HPC to instruction-tuning Llama 3.

Key projects:

• DeepSeek R1 Distillation — Boosted Qwen2.5-Math-7B accuracy from 13.3% to 56.7% on AIME 2024 via SFT + GRPO across 8 H100 GPUs. Details →
• Llama 3 Sentiment Analysis — Fine-tuned Llama 3.1–8B achieving 81.49% accuracy on MTEB tweet sentiment. Details →

Explore all LLM Distillation & Fine-Tuning projects →

---

Generative AI & Applied Machine Learning

Developing and fine-tuning generative models for image synthesis, as well as applying advanced deep learning architectures to real-world predictive modeling and audio processing tasks.

 

Key projects:

• Stable Diffusion LoRA — Fine-tuned SD v2 with LoRA for Naruto-style generation, with 77% training time reduction via multi-GPU. Details →
• Bike Traffic Prediction — Graph Attention Networks for urban traffic forecasting; 2nd place at BTW 2023. Details →
• Speaker Identification — Transformer/Conformer encoders achieving 91.8% accuracy. Details →
• Anime Face Generator — Diffusion probabilistic model trained on 71k anime faces. Details →

Explore all Generative AI & Applied Machine Learning projects →