currently learning

• cuda, metal, parallel optimizations for gemm
• gpu architecture

ml work

• bert finetuning - entailment for rag application citations
• rec sys - content embedding based recommendations
• retrieval - hybrid site search, retrieval augmented gen

websites

• llm evaluator - prompt+model evals, dual chat comparison, more
• dialstructure - audio transcription, diarization, summarization, classification
• ai academic advisor - gemini based academic advisor for utsa programs

tools

• lambda labs client - manage gpu clusters with a python client
• groq-nvim plugin - ai code gen in vim

studies

• pii benchmarking - perf benchmarking of aws, gcp, azure pii services

contributions

• mlflow
• flyte
• chroma db