Freelancers using RoBERTaFreelancers using RoBERTa
ProjectsPeople
Trashu Vashisth's avatar
Trashu Vashisth
Delhi, India
Building Production-Grade AI Agents & RAG Systems
10
Followers
Building Production-Grade AI Agents & RAG Systems
Cover image for Developed a high-precision Resume Parser using a
Developed a high-precision Resume Parser using a custom-trained RoBERTa model, specifically fine-tuned for Named Entity Recognition (NER) tasks. This tool automates the extraction of critical information from unstructured resumes with deep learning accuracy. Key Features: NER-Based Extraction: Accurately identifies entities like Name, Experience, Skills, Education, and Contact Info. RoBERTa Architecture: Leverages Transformer-based embeddings for superior contextual understanding compared to traditional parsers. JSON Output: Seamlessly converts complex resume layouts into structured JSON format for easy database integration and ATS (Applicant Tracking System) workflows. High Accuracy: Trained to handle diverse formatting and professional jargon.
3
198
Cover image for Developed a production-grade Retrieval-Augmented Generation
Developed a production-grade Retrieval-Augmented Generation (RAG) system specifically designed to automate the analysis of complex Environmental, Social, and Governance (ESG) reports. This tool bridges the gap between static LLMs and the dynamic, data-heavy requirements of legal and sustainability compliance. [1 (https://www.youtube.com/watch?v=wkYPcMtwlN8)] Key Features & Capabilities Intelligent Document Processing: Automatically handles large, unstructured PDF/Word ESG reports, extracting critical clauses and metrics in seconds. Fact-Grounded Q&A: Uses a RAG architecture to ensure all answers are strictly based on the uploaded documents, virtually eliminating AI hallucinations. Compliance Mapping: Cross-references internal company data with global frameworks like CSRD, GRI, and TCFD to identify gaps or inconsistencies. Audit-Ready Traceability: Every insight generated includes direct citations and excerpts from the source files, providing a clear "paper trail" for legal teams. Automated Drafting: Capability to draft legal summaries, notices, or internal policy updates based on analyzed ESG risks Note: The 'Slaughter and May' branding in the sidebar is for UI/UX demonstration purposes only, showcasing how the tool integrates into a top-tier law firm's environment. #AI #RAG #LegalTech #ESG #Python #LangChain
1
62
Cover image for Developed a full-stack RAG-based E- Commerce
Developed a full-stack RAG-based E- Commerce AI chatbot using React.js and Tailwind CSS that suggests the perfect laptop from a live catalog. Integrated ChromaDB with BGE Embedding models to provide highly accurate, context-aware product recommendations and instant technical support." Key Highlights: Smart Laptop Recommendations: Uses Semantic Search to match user needs (gaming, coding, etc.) with real-time specs. Advanced Tech Stack: Powered by LangChain for orchestration and BGE models for superior data retrieval. Modern UI/UX: Built a responsive, clean interface using React.js and Tailwind CSS. Zero Hallucination: Ensures all suggestions are strictly grounded in the available product inventory.
2
1
154
Cover image for Built a highly scalable Retrieval-Augmented Generation
Built a highly scalable Retrieval-Augmented Generation (RAG) chatbot designed to interact with private datasets/PDFs. Unlike standard LLMs, this system minimizes hallucinations by retrieving real-time context from a local knowledge base before generating responses. Key Features: Semantic Search: Implemented Vector Embeddings to perform high-speed similarity searches across thousands of document chunks. Smart Retrieval: Integrated a retrieval pipeline using LangChain to fetch the most relevant context for user queries. Source Citation: Configured the bot to provide source references from documents, ensuring data transparency and accuracy. Optimized Performance: Used FAISS/Chromadb for efficient vector storage and retrieval.
4
228
RoBERTa(1)
Mansi Gaikwad's avatar
Mansi Gaikwad
Pune, India
Web Developer | Responsive Design & UI/UX Specialist
New to Contra
Web Developer | Responsive Design & UI/UX Specialist
Cover image for Project Title: Sentix AI: Global
Project Title: Sentix AI: Global Sentiment Intelligence Results & Impact: 1. Achieved a 92% F1-score by implementing domain-specific fine-tuning on diverse consumer datasets, ensuring high reliability in classification. 2. Engineered an Aspect-Based Sentiment Analysis (ABSA) module that decomposed reviews into granular attributes (performance, pricing, reliability), making trend tracking 15% more precise. 3. Optimized inference performance by 25% through model distillation and Docker-based containerization, enabling the system to handle thousands of concurrent requests. 4. Mitigated data bias by designing a robust pre-processing workflow including lemmatization and custom noise reduction, critical for handling global marketplace jargon.
0
31
Cover image for Project Title: SteganoTool 1. Established a
Project Title: SteganoTool 1. Established a critical security framework for digital forensics and covert communication, as published in the IJRTI Journal (Vol. 10, Issue 4). 2. Achieved 100% data integrity during extraction by engineering a lossless LSB substitution pipeline for image, audio, and text carriers. 3. Conducted a comparative analysis of LSB vs. advanced transformation methods, proving that my custom noise-reduction heuristics significantly improved the PSNR (Peak Signal-to-Noise Ratio). 4. Optimized for multi-format compatibility, supporting 24-bit RGB and 8-bit grayscale images, making the tool versatile for various enterprise security applications.
0
24
Cover image for Engineered a dynamic, multi-section input
Engineered a dynamic, multi-section input engine that optimized the user journey through scalable, real-time block management logic. Validated a 30% improvement in form-filling efficiency by measuring user interaction speed against traditional static document templates. Developed and owned a live-preview rendering engine with CSS-optimized print functions to ensure 100% document fidelity and recruiter-ready formatting.
0
50
Cover image for Architected a high-performance frontend engine
Architected a high-performance frontend engine using Vanilla JavaScript and Tailwind CSS, resulting in a 40% increase in UI responsiveness compared to standard CSS frameworks. Engineered a client-side recommendation algorithm using Local Storage, dynamically analysing user behavioural data to suggest niche titles with a 100% data persistence rate without a backend. Optimized user decision-making by implementing a real-time price comparison modal, increasing the application’s utility and simulation accuracy by 30% across mock retail datasets.
1
81
RoBERTa(1)
Matteo Caprio 's avatar
Matteo Caprio
Rome, Italy
Economist and Marketeer with a passion for business strategy
New to Contra
Economist and Marketeer with a passion for business strategy
Cover image for ISE Omnichannel experiences analysis and implementation
ISE Omnichannel experiences analysis and implementation
0
0
Cover image for Colnago Innovation Project
Colnago Innovation Project
0
0
Cover image for Liberia palm oil industry
Liberia palm oil industry
0
0
Cover image for AW Lab Brand Audit
AW Lab Brand Audit
0
0
RoBERTa(1)