🤖 LLM Systems & Post-Training Researcher | 🛠️ Agentic AI Engineer
Building intelligent AI systems that bridge models, agents, and human experiences — from high-performance LLM infrastructure to voice-enabled desktop companions.
I focus on:
- Efficient LLM architectures and attention mechanisms
- Post-training algorithms (SFT, DPO, GRPO, RLHF)
- Agent systems and tool-augmented AI
- Multimodal interaction with voice, vision, and real-time experiences
-
🤖 flash-linear-attention
— Efficient implementations for emerging model architectures.
-
🧠 tilelang
— Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
- 🧭 Codev — Full-featured agentic coding workspace with ToolSearch, SubAgent Swarm, and auto-compact context management
- 🤖 Codev Studio — Desktop home for your Codev coding agents. Terminals front and center, editor when you need it
- 🧠 Omni — Multimodal LLM framework: train LM, VLM, and full speech models from scratch; real-time voice/video call
🌊 Partial Multi-View Clustering via Meta-Learning and Contrastive Feature Alignment
"Build what you'd want to use yourself" — Every project starts as a personal need, then grows into something others can benefit from.
Random Facts
- Ani started as a weekend experiment, grew into a full desktop companion platform
- Runs multiple AI models in parallel for different tasks
- Deeply invested in making AI interaction feel natural, not robotic
- Constantly exploring new ways to bridge terminal AI with rich desktop experiences