AI Engineer specializing in multimodal agentic systems and scalable intelligent architectures. Experienced in fine-tuning LLMs, orchestrating autonomous workflows, and deploying production-grade AI applications. Passionate about shifting software from data processing to genuine cognitive agency.

Orchestrating the development of production-grade multimodal applications and autonomous agents. Engineering fine-tuning pipelines and complex AI workflows to shift systems from static processing to dynamic cognitive agency. Implementing rigorous evaluation frameworks to benchmark and align model performance with product objectives.

Automated core operational workflows by engineering research-driven prototypes using multimodal and large language models. Optimized model outputs through advanced prompt engineering and the design of vision-language processing pipelines, significantly enhancing organizational efficiency.

Generated high-complexity code evaluation datasets to align large language models (RLHF). Audited model outputs for logical correctness and security vulnerabilities.

Built a local-first multimodal video search engine with Gemini and ChromaDB, reducing natural language content lookup times by 90%.

Tech: Python, Gemini API, ChromaDB, FFmpeg, React.

Built a lightweight autonomous agent using Gemini (vision/planning) and Playwright (action execution) to automate Chromium workflows with typed actions and fully inspectable run artifacts.

Tech: Google AI SDK, Playwright, FastAPI.

Developed ground-up neural network implementations with comprehensive technical notes and research paper breakdowns.

Tech: Python, NumPy, Jupyter, Pytorch.

Built a fully offline, edge AI triage assistant on Mac Mini M2 8GB that extracts patient data from paper forms using Gemma 4 E2B and scores clinical priority deterministically.

Engineered an automated MCQ generation and evaluation pipeline using Gemini 2.5 Flash, leveraging custom rubrics to cut processing times and achieve 99%+ structured data accuracy.

Tech: GoogleAI SDK, PostgreSQL, Pandas

Developed a multi-agent system with Google's ADK to automate root-cause diagnosis across system logs, metrics, and code changes.

Tech: Python, Google ADK, Multi-Agent Systems.

This Google DeepMind course explores the transformer architecture — covering attention mechanisms, multi-head attention, and language model internals through hands-on activities.

Relevant coursework: Digital Signal Processing, Computer Networks, Analog

and Digital Circuits, Operating Systems, Embedded systems, Artificial

Intelligence, and Machine Learning.

Fluent English, Hindi and Kannada.

I love stumbling upon topics that let me dive into deep rabbit holes, Weight training, books and Football.