App LogoApp name
AS

Abhimanyu Sharma

Open to work1 years experience

Full Stack AI Developer

Gorakhpur, Uttar Pradesh, IndiaTarget Roles: Backend Engineer • Full-Stack Developer • Frontend Specialist

Full Stack AI Developer and Machine Learning enthusiast.

GitHubLinkedIn
Resume
Email

Standing Rank

Rank Not Available

Developer Badges

Badges Pending

Skills & Technologies

37 skills
cc++javapythonjavascripthtmlcssreact.jsnode.jsnext.jsexpressfast apisrest apistensorflowpytorchscikit-learnkeraslangchainopencvnltkspacygensimpandasnumpylarge language models (llms)retrieval-augmented generation (rag)prompt engineeringagentic workflowspostgresqlsqlgcpazuregitgithubvs codelinuxwindows

Work Experience

Full Stack AI Developer Intern

Innovacio Technologies

Dec 2025 - Present Remote
  • Built an AI-powered product recommendation module using machine learning models, integrated into the platform to surface personalized results based on user behavior.
  • Developed responsive frontend interfaces in Next.js to present AI recommendation outputs, improving usability and reducing the time users spent finding relevant products.
  • Connected frontend components to REST APIs serving AI model predictions; coordinated with backend engineers to ensure stable and consistent data delivery across environments.
  • Wrote Express.js route handlers and middleware to structure API payloads, validate request data, and pass clean inputs to the AI recommendation layer.

Projects

Multi-Class News Classification System

View Project
PythonTensorFlowKerasNLTKSpaCyGensimWord2Vec
  • Trained an NLP text classification model on 120,000+ news articles across four categories, reaching 91% accuracy after iterative hyperparameter tuning.
  • Built a preprocessing pipeline using NLTK and SpaCy for tokenization, lemmatization, and normalization; used Google Word2Vec embeddings for semantic feature representation.
  • Designed a deep learning model with stacked Bidirectional LSTM layers, Dropout, and Batch Normalization to reduce overfitting and improve generalization on held-out data.

Hybrid Object Detection Pipeline

View Project
PyTorchOpenCVMask R-CNNFaster R-CNNHugging FacePyTesseract
  • Combined Mask R-CNN and Faster R-CNN on a custom dataset of 5,000+ images, achieving 94.57% detection accuracy across multiple object categories.
  • Automated text extraction using PyTesseract OCR, exporting structured data to CSV/JSON with 98% labeling precision for downstream analytics use.
  • Added a post-processing stage using DistilBART (Hugging Face) to generate contextual metadata summaries, scoring 89.6% relevance via manual evaluation.

Custom Game Engine (Shunya)

View Project
C++OpenGLImGuiEnTTyaml-cppPremake5MSVC
  • Built a modular game engine in C++ with a custom Entity Component System (ECS) using EnTT, featuring a real-time event loop, scene serialization via yaml-cpp, and a working editor layer.
  • Implemented a 2D batch renderer using OpenGL with texture atlasing and vertex buffer management; integrated ImGui for live scene inspection, component editing, and debugging tools.
  • Structured the codebase as separate core library, editor, and runtime targets using Premake5, keeping engine internals decoupled from application-level game logic.

Leaderboard Standings

Leaderboard Position Pending

Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.

Assessment Highlights

Assessments Not Completed

Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.

AI Collaboration Score

AI Collaboration Score Pending

Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.

Role Compatibility Profile

Role Compatibility Analysis Pending

Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.

Achievements

Design and Performance Optimization of a Modular 2D/3D Game Engine Architecture

Proposed a modular 2D/3D engine architecture that separates editor, core, and runtime subsystems to improve performance isolation and long-term maintainability.

About Details

Professional Bio

Full Stack AI Developer with expertise in machine learning, NLP, and game engine architecture. Experienced in building AI-powered recommendation systems and developing responsive web applications using Next.js and Express.js.

Bachelor of Technology – Artificial Intelligence and Machine Learning in Artificial Intelligence and Machine Learning

Institute of Technology and Management, Gorakhpur, Uttar Pradesh ( - 2026)

Languages: English, Hindi
Email: Locked