I specialize in AI evaluation, LLM infrastructure, and quality assurance for production-grade systems. Currently focused on end-to-end RAG development, automated evaluation pipelines, and multi-modal model testing to ensure reliable, high-precision AI outcomes.
Languages
AI / LLM
Frameworks / Platforms
Tools
- RAGAS Evaluation Framework Integration β integrated automated evaluation across end-to-end RAG systems.
- Multi-modal AI Testing β built visual evaluation datasets and benchmarking workflows for VLMs.
- Automated Evaluation Pipelines β designed modular βevalsβ framework for one-click benchmarking and insights.
- Speech & Voice AI QA β fine-tuned Whisper for ASR optimization and production-grade voice agents.
From: 29 April 2026 - To: 29 May 2026
Total Time: 185 hrs 28 mins
Python 67 hrs 39 mins βββββββββββββββββββββββββ 35.10 %
JSON 41 hrs 4 mins βββββββββββββββββββββββββ 21.31 %
Markdown 30 hrs 9 mins βββββββββββββββββββββββββ 15.65 %
Text 15 hrs 22 mins βββββββββββββββββββββββββ 07.97 %
Bash 10 hrs 41 mins βββββββββββββββββββββββββ 05.55 %
Other 7 hrs 17 mins βββββββββββββββββββββββββ 03.78 %
CSV 4 hrs 37 mins βββββββββββββββββββββββββ 02.40 %
Git Config 3 hrs 5 mins βββββββββββββββββββββββββ 01.60 %
TOML 3 hrs 4 mins βββββββββββββββββββββββββ 01.60 %
Jinja2 2 hrs 49 mins βββββββββββββββββββββββββ 01.47 %