Go-based automation for generating docker-compose.yml files from user-defined topology and interface inputs.

Simplifies SONiC test deployments using docker-sonic-vs and improves lab setup workflows with Cobra CLI validation and Bash automation.

Real-time lecture companion with live transcription, multilingual support, slide-deck sync, and in-session AI learning tools.

Used Deepgram, Gladia, and Google Gemini to generate lecture summaries, flashcards, graded practice exams, Q&A, and jargon explanations.

Benchmark for evaluating LLM performance in multi-turn, preference-driven code translation.

Supported scalable AI systems experiments with Docker workflows, AI APIs, data pipelines, and Google Cloud compilation/testing infrastructure.

Automated code transformation pipeline translating PyTorch ML workloads into JAX.

Coordinated staged validation and generation using Hugging Face LLMs, evaluating Qwen, CodeLlama, and Mistral for generated code correctness.