Mohit Goyal

• Currently: Contributing to the development of a scalable and efficient AI agents using Langchain, LangGraph, and Next.js.

• Co-developed GRIT(Geometric Reprojection Instruction Tuning), a novel instruction tuning framework that fine-tunes ¡1% of LLM parameters (0.997%) while outperforming full fine-tuning and LoRA on benchmarks (BLEU ↑26.2, ROUGE-L ↑34.9 on Alpaca). • Fine-tuned multiple LLMs including GPT-2 (355M), LLaMA-3B, and Mistral-7B, demonstrating up to 30% parameter savings without performance loss, reducing compute and memory costs by 40%. • Conducted rigorous ablation studies comparing GRIT vs. LoRA, QLoRA, and AdaLoRA, validating 2.1 BLEU and 2.5 ROUGE-L gains with GRIT’s geometry-aware updates.

• 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.