Work Experience

• Built and deployed production-grade AI systems at C3ALabs, focusing on reliability, latency, and real-user usage not demos.

• Developed agentic AI features (artifacts, agent skills, multi-agent orchestration) and shipped them to production, ensuring performance under real-world constraints.

• Designed and productionized advanced RAG pipelines using Google File Search APIs, handling document chunking, retrieval quality, and response grounding in production environments.

• Core contributor to applied AI R&D experimented with Claude skills, MCP-based tool routing (Composio), and multi-agent coordination patterns, turning research ideas into deployable systems.

• Co-authored a research paper on Large Language Model (LLM) fine-tuning - arXiv:2601.00231

• Developed GRIT (Geometric Reprojection Instruction Tuning) a framework fine-tuning only 0.997% of LLM parameters while outperforming full fine-tuning and LoRA on standard benchmarks.

• Fine-tuned multiple LLMs (GPT-2 355M, LLaMA-3B, Mistral-7B) achieving 30% parameter savings with 40% reduction in compute & memory costs without compromising accuracy.

• Conducted extensive ablation studies validating GRIT's geometry-aware updates over LoRA, QLoRA, and AdaLoRA.

• Benchmarked GRIT across diverse NLP tasks on datasets including Alpaca, Dolly-15k, BoolQ, and GSM8K.

• Autonomous Market Research Agent: Developed an agent that automates market and competitor research using real-time data collection, web search, and report generation for business insights.

• AI Voice Interviewer: Built and deployed a voice-based AI interviewer to conduct inbound calls, capture candidate responses, and generate structured interview summaries.

• Personalized Front Desk Agent: Created a multimodal front desk AI agent capable of handling text, voice, and video inquiries for customer support and client onboarding processes.

• Whatsapp and Social Media Automation Agent: Engineered agents that automate group administration, content posting, and engagement analysis on WhatsApp and other social platforms.

• Credit Risk Analysis Agent: Designed a credit risk agent using custom ML models to evaluate applicant default risk and streamline lending decisions with automated scoring and documentation.

• Outbound Calling Platform Agent: Deployed outbound calling agents capable of scheduling, executing, and logging calls for lead generation and customer feedback with seamless voice pipeline integration.