Rohit S.
Lead AI Scientist
Experience
Jun 2024 - Present
1 year 7 monthsLead AI Scientist
Insight Global
- Led the development of an Intelligent Document Processor implementing Multimodal RAG architecture with LlamaParser and GPT4-0, leveraging LLM as judge for quality control and validation. Achieved 95% accuracy in processing various financial documents through dual-LLM architecture where secondary LLM Gemini acted as judge for output validation. Implemented custom evaluation metrics for automated assessment of extracted data quality, reducing manual processing time by 70% while maintaining high accuracy across invoices, bank statements, and regulatory documents.
- Built a multi-modal data extraction system leveraging Lang-chain, lang-graph, and a vision-based LLM to parse 50,000+ monthly scanned policies, handwritten claims, and PDF endorsements. The pipeline combined visual layout understanding (tables, stamps, signatures) with advanced prompting to achieve 93% field-level accuracy for structured extraction of policy terms, coverage limits, and claim histories.
- Leading the development of a flagship AI assistant, contributing to a differentiated product offering that streamlined core operations and enhanced client engagement in the financial domain, strengthening market position and supporting the company’s recent $63 million Series C funding.
Feb 2023 - Jun 2024
1 year 5 monthsLead Data Scientist
Adventure India
- Designed and deployed a personalized hotel recommendation engine using AWS Personalize, integrating multi-source data (user clickstreams, interaction history, hotel descriptions, customer reviews, and Google Analytics user profiles). Trained a contextual recommendation model by combining behavioural, demographic, and content-based signals, then hosted the solution on AWS SageMaker for real-time inference. Automated daily batch predictions via cron jobs to trigger personalized trip suggestions and notifications for users’ upcoming travel plans, improving engagement by 30% and driving a 25% lift in booking intent across targeted campaigns.
- Designed and deployed an advanced RAG system for personalized hotel discovery, integrating customer prompts with a semantic search engine trained on hotel embeddings (derived from descriptions, reviews, and amenities). The solution retrieves contextually relevant matches by comparing user queries against precomputed hotel embeddings stored in AWS OpenSearch, returning the top five recommendations ranked by similarity. Upon user selection, a conversational AI chatbot engages users in dynamic Q&A, providing granular details (e.g., pricing, policies, nearby attractions) and seamlessly redirecting to booking pages post-interaction.
Oct 2021 - Feb 2023
1 year 5 monthsSenior Consultant, Data Science & Engineering
Alliantgroup India
- Developed and deployed an attention-based LSTM model to optimize business development team strategies by analysing historical conversational data between BD representatives and organizational leads. Trained on NLP-pre-processed transcripts, the model identifies patterns in successful negotiation tactics, objection handling, and lead conversion signals. The architecture integrates bidirectional LSTM layers with attention mechanisms to prioritize critical conversational segments (e.g., pricing discussions, timeline alignment) and predict optimal follow-up actions.
- Developed and deployed a personalized customer communication engine leveraging a hybrid machine learning approach: first applying ensemble-based clustering to segment customer data, followed by classification models to predict best messaging channels. The solution was hosted on AWS SageMaker for scalable inference and configured with cron jobs to automate daily batch predictions. This end-to-end pipeline achieved 85% prediction accuracy and a balanced F1 score, driving measurable improvements in customer engagement and conversion rates across platforms including Epsilon, Attentive, and Snowflake.
Sep 2018 - Oct 2021
3 years 2 monthsNLP Engineer
My Next Film Private Limited
- Built a movie script processing pipeline using SpaCy’s model to automatically extract structured elements (speakers, dialogues, scene transitions) from raw scripts. Integrated the NLP outputs with a Narration Room interface, built using MoviePy for scene visualization, Pillow for image processing, and FPDF for script PDF generation, enabling writers to annotate, edit, and preview scripts in a unified environment.
- Deployed AI-powered sentiment analysis and payment integration for a SaaS platform. Trained a seq2seq LSTM model on 50,000+ annotated dialogues to evaluate emotional and sentiment polarity (positive/neutral/negative) in screenplays, achieving 89% accuracy (F1-score).
Summary
A highly accomplished AI Scientist with 7 years of expertise in Generative AI, Machine Learning, Data Science and Cloud-based ML solutions, specializing in cutting-edge solutions for fintech, retail, e-commerce and travel industries. Combines deep technical proficiency in LLMs (OpenAI, Llama, MoE), RAG architectures, and AI agents with a proven track record of delivering enterprise-scale AI systems that drive operational efficiency, revenue growth and contribute to significant company valuation and successful funding rounds, including a recent $63M Series C.
Languages
English
AdvancedEducation
Aug 2015 - May 2019
Giani Zail Singh College of Engineering and Technology
Bachelor of Technology, Computer Science & Engineering · Computer Science & Engineering · Bathinda, India
Need a freelancer? Find your match in seconds.
Try FRATCH GPT More actions
Similar Freelancers
Discover other experts with similar qualifications and experience
- English
- Deutsch
2025 © FRATCH.IO GmbH. All rights reserved.