Aaditya Barak
AI & Backend Engineer - LLMs, RAG Systems, Document Intelligence
Education
UIET, Panjab University - Bachelor of Engineering, Electrical & Electronics Engineering
Sep 2022 - May 2026 | Chandigarh, India
Experience
PrudentBit - AI & Backend Engineer
Feb 2026 - Present | Noida, Uttar Pradesh
- Migrated the backend to on-premise deployment using Docker, containerizing services and managing infrastructure for backend and AI workloads
- Integrated OnlyOffice into the product for in-app document editing and collaboration workflows
- Migrated LLM inference to ONNX runtime and optimized Django backend services for improved performance
- Implemented a software licensing system for the platform
PrudentBit - AI Intern
May 2025 - November 2025 | Noida, Uttar Pradesh
- Led development of a production-grade document redaction system for PDF, DOCX, and images, reducing manual effort by 70% across 1,000+ documents
- Built an end-to-end document AI pipeline using OCR, preprocessing, PII detection, and masking, improving processing speed by 2x
- Developed PII detection with pixel-level masking while preserving layout
- Added TinyBERT-based reranking at roughly 100ms for better search relevance
Freelance AI Engineer - Client Projects
May 2025 - Present | Remote
- ZapUp - AI Educational Platform: Built a full-stack platform with real-time chatbot, personalization, and scalable backend using Next.js and Supabase
- Implemented a context-aware LLM assistant with conversation memory and dynamic filtering
- TITTA - AI Construction Analysis System: Built a production-grade RAG system for querying PDFs and CAD files
- Implemented vector search using BGE-large embeddings with Supabase vector storage
- Designed a DWG/DXF metadata extraction pipeline with structured PostgreSQL storage for domain-specific engineering reasoning
Projects
AI-Powered Resume Parser & Job Matcher
FastAPI, PostgreSQL - November 2025
- Built AI system using OCR + NER + LLM scoring to process 1,000+ resumes
- Implemented multi-criteria ranking that reduced recruiter effort by 40%
BERT NER System
Transformers, PyTorch - July 2025
- Built a token classification model using HuggingFace Transformers and PyTorch
- Improved performance using fine-tuning and preprocessing
Deepfake Detection System
TensorFlow - April 2025
- Achieved 93% accuracy using VGG16 transfer learning
- Evaluated model performance across real vs synthetic datasets
Technical Skills
- Languages: Python, SQL, JavaScript
- AI/ML: PyTorch, Transformers, NLP, Computer Vision, OCR
- LLM & GenAI: LLMs, Prompt Engineering, RAG, LangChain, Vector Search
- Frameworks: FastAPI, Next.js
- Databases: PostgreSQL, Supabase, Redis
- Tools: Git, Linux, Docker
Open Source and Developer Community - Contributor / Mentor
2022 - Present | Panjab University
- Contributed to ML/NLP repositories and mentored developers on APIs and deployment