AI Development Projects in GurugramAI Development Projects in Gurugram
Projects
People
Cover image for AI Resume Screening | Candidate
AI Resume Screening | Candidate Ranking System | AI HR Recruiter | ATS CV/Resume Optimization 𝗢𝘃𝗲𝗿𝘃𝗶𝗲𝘄 Recruiters often spend hours manually reviewing resumes, comparing candidate qualifications, and identifying the best fit for open positions. To address this challenge, I developed an AI-powered Resume Screening and Candidate Ranking Platform that automates candidate evaluation, improves hiring efficiency, and reduces recruitment time. 𝗖𝗵𝗮𝗹𝗹𝗲𝗻𝗴𝗲 Traditional recruitment processes involve reviewing hundreds of resumes for a single position. This manual approach is time-consuming, inconsistent, and often results in qualified candidates being overlooked. Recruiters needed a solution capable of quickly analyzing resumes, matching them against job requirements, and generating reliable candidate rankings. 𝗦𝗼𝗹𝘂𝘁𝗶𝗼𝗻 I built an intelligent recruitment platform that leverages Artificial Intelligence and Natural Language Processing (NLP) to automate resume analysis and candidate assessment. 𝗞𝗲𝘆 𝗳𝗲𝗮𝘁𝘂𝗿𝗲𝘀 𝗶𝗻𝗰𝗹𝘂𝗱𝗲: - ATS-compatible resume parsing for PDF and DOCX files - Automated extraction of skills, experience, education, certifications, and contact information - AI candidate matching based on job descriptions - Intelligent candidate scoring and ranking system - Semantic skill matching using NLP techniques - Automated shortlist generation for recruiters - Recruiter dashboard for managing applications and rankings - Bulk resume processing for high-volume recruitment - Interview recommendation system based on candidate fit - Fair and consistent evaluation framework to reduce manual bias 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗣𝗿𝗼𝗰𝗲𝘀𝘀 The platform was designed with scalability and accuracy in mind. The workflow begins by parsing uploaded resumes and extracting structured candidate data. AI models then compare candidate profiles against job requirements, analyzing technical skills, years of experience, educational background, and industry relevance. A ranking engine generates compatibility scores and presents candidates in order of suitability. Recruiters can review detailed scoring insights, compare applicants, and make faster hiring decisions. 𝗥𝗲𝘀𝘂𝗹𝘁𝘀 The solution significantly improved recruitment efficiency and candidate discovery. 𝗢𝘂𝘁𝗰𝗼𝗺𝗲𝘀 > Reduced manual resume screening time by up to 80% > Accelerated candidate shortlisting process > Improved recruiter productivity and hiring speed > Increased consistency in candidate evaluation > Enabled processing of hundreds of resumes within minutes > Enhanced talent identification through AI-driven matching 𝗖𝗼𝗻𝗰𝗹𝘂𝘀𝗶𝗼𝗻 This AI recruitment platform transforms traditional hiring workflows by automating resume screening, ranking candidates intelligently, and helping recruiters identify top talent faster, more accurately, and at scale.
1
185
Cover image for Built and maintained a HIPAA
Built and maintained a HIPAA compliant production medical AI scribe system that uses multi-step LLM agents to extract clinical entities directly from physician-patient conversations and turn them into structured medical notes, cutting down the manual transcription work clinicians used to do after every visit. Multi-stage clinical workflow: Documentation, coding, and review each have different logic and conditional paths, and the system needed to branch correctly between them without losing context. Clinical accuracy: Generated notes had to be grounded in real patient history and clinical guidelines, not just plausible-sounding text. Production reliability: As a live system handling real conversations, every agent run needed to be observable, debuggable, and monitored for cost and latency in real time. Non-technical requirements gathering: Clinical needs had to be captured accurately from stakeholders without a technical background and translated into precise agent logic. Approach: Stateful agent orchestration with LangGraph Designed LangGraph-based agent workflows with conditional branching, allowing the system to move correctly across documentation, coding, and review stages based on conversation content. Context-grounded note generation with RAG Built a RAG pipeline on AWS Bedrock with embeddings, so every generated note is grounded in the patient's actual history and relevant clinical guidelines rather than generic output. Full production observability Integrated Langfuse across all agent runs to track token usage, latency, and model KPIs, giving the team visibility into system health and cost in production, not just at build time. Clinical stakeholder collaboration Ran requirements sessions directly with clinical staff, converting their documentation needs into concrete agent behavior specs and validation criteria. Results & Impact: ~40% reduction in manual transcription time for clinicians using the system. Clinically grounded output, with notes tied to real patient history and guidelines instead of unsupported generation. Full production observability, with token usage, latency, and model performance tracked continuously. A workflow clinicians could trust, built through direct collaboration rather than a black-box handoff. Provided Services & Solutions: 📌 AI Agent Development (LangGraph) 📌 RAG Pipeline Development (AWS Bedrock) 📌 LLM Observability (Langfuse) 📌 Cloud Infrastructure (AWS Lambda, S3, DynamoDB) 📌 Stakeholder Requirements Translation 📌 Production ML Systems Tech Stack Python · LangChain · LangGraph · AWS (Bedrock, Lambda, S3, DynamoDB) · Langfuse · TypeScript · REST APIs
2
72
Cover image for The Problem: Sales teams waste 60%
The Problem: Sales teams waste 60% of their time researching leads instead of closing them. The Solution: I built a custom Agentic AI Pipeline that automates deep-dive business intelligence and lead scoring. Key Technical Highlights: Multi-Agent Architecture: Built using CrewAI, featuring a 'Business Intelligence Specialist' (for real-time research) and a 'Senior Sales Director' (for strategic scoring). High-Speed Intelligence: Powered by Llama 3.3-70B  for near-instant reasoning and decision-making. Real-time Web Scoping: Integrated Tavily AI to fetch live revenue data, employee counts, and market positioning. Enterprise Storage: A robust SQLite backend to manage lead pipelines with a sleek Streamlit dashboard. Smart Throttling: Engineered custom rate-limiting and token-trimming logic to ensure 99.9% uptime even under heavy API constraints. How it works: Simply enter a company name and URL. The AI agents scour the web, analyze the company's "AI potential," calculate a priority score (0-100), and even write a personalized sales pitch—all in under 30 seconds.
0
85
Cover image for Now, meet the one I
Now, meet the one I already told you all my project jarvis which is complete now. Here's the details - JARVIS is a production-grade, privacy-first AI desktop assistant designed to operate fully locally on standard hardware. Built to rival modern desktop AI systems, JARVIS seamlessly integrates natural voice interaction, real-time screen vision comprehension, deep Windows OS automation, and intelligent document/presentation generation. Unlike basic wrappers around cloud APIs, JARVIS features a hybrid architecture combining zero-latency regex intent routing, local LLM fallbacks, Win32 API shell controls, and active VLM screen verification. Key Capabilities of Jarvis - 🎙️ Multimodal Voice & Audio Intelligence Bilingual STT & Dynamic Query Cleaning: Real-time speech recognition tuned for Hinglish, Hindi, and English with automatic phonetic filler word stripping. Expressive Local TTS & Emotion Effects: Low-latency neural speech synthesis powered by Piper ONNX and Edge TTS with adaptive prosody and emotional modulation. Hands-Free Media & Non-API Automation: Full hardware media key automation for Spotify and browser video playback without requiring paid API tokens. 👁️ Vision AI & Live Screen Comprehension VLM Window & Screen Verification: Captures active window frames using OpenCV and local vision models (Moondream / Qwen-VL/Mistral) to verify OS tasks (e.g., verifying opened folders, app states, or UI elements). Camera Emergency Sentinel: Real-time visual distress sentinel using multimodal vision checks before initiating priority emergency calls. 🖥️ Deep OS & File System Automation Subfolder Inspection & Bulk Purging: Inspects complex nested folder structures (e.g., Pictures/Screenshots), calculates storage footprints, and executes secure file/folder purges via Win32 shell calls. OneDrive-Aware Name-Based Resolution: Intelligent 3-tier lookup engine resolving standard paths (Desktop, Downloads, Pictures) across native paths and OneDrive redirects without needing absolute user paths. Silent Recycle Bin Clean & Disk Optimization: Win32 API integration (SHEmptyRecycleBinW) for 100% silent, error-free disk maintenance. 📄 Productivity & AI Document Generation Automated Presentation Engine: Generates styled PowerPoint presentations (.pptx) with custom slide themes, topic summaries, and automated asset downloads. Markdown & PDF Document Compiler: Built-in Marp compilation engine converting voice notes to polished PDF slides and documents. And not only that I have open-sourced the entire github repo you can install it, check it and run it to your laptop as your assistant too, and don't forget to give the star, and if you face any issue kindly dm me or message in github too. Here's the link - "https://github.com/darshitp091/Jarvis "
2
199