Currently, changing my readme file. Thank you for your patience!
🔬 Researching and building agentic AI systems, LLM inference architectures, and automation-first intelligence pipelines.
My work sits at the intersection of data science, machine learning systems, and autonomous agents, with a strong focus on scalability, evaluation, and real-world deployment.
-
Agentic AI & Autonomous Systems
- Single-agent and multi-agent architectures
- Tool-using agents (APIs, databases, code execution)
- Planning, memory, and control loops
- Agent orchestration and task decomposition
-
LLM Inference & Systems
- Efficient inference (latency, throughput, cost)
- Model routing and hybrid LLM architectures
- RAG systems and retrieval strategies
- Evaluation, benchmarking, and failure analysis
-
Applied Data Science
- Statistical modeling & experimentation
- Predictive analytics & decision systems
- Data-centric AI workflows
- Bridging classical ML with foundation models
- 🤖 AI Agents for complex, real-world workflows
- ⚡ Production-grade LLM inference pipelines
- 🔁 Automation systems with AI-in-the-loop
- 🧠 Hybrid architectures: Classical ML + LLMs
- 📏 Evaluation frameworks for agent behavior
Intelligence is not just model capability — it’s architecture, evaluation, and integration.
I value:
- Reproducibility & clean abstractions
- System-level thinking
- Rigorous evaluation over demos
- Production-aware research
- 🔬 Open to research collaborations in AI agents & LLM systems
- 🧠 Interested in agent evaluation, inference optimization, and applied AI research
- ⭐ If my work helps you, feel free to star or fork a repo