Headline

Computer Vision & ML Engineer | Process Automation & Client-Facing Delivery | SQL • OpenCV • TensorFlow • ServiceNow

About

I build production-ready Computer Vision and Machine Learning systems that integrate into real products, not just research prototypes. My work focuses on designing end-to-end CV and ML pipelines, from data processing and model development to API-based deployment and integration. Alongside my CV/ML work, I bring hands-on professional experience in enterprise process automation and stakeholder management — currently at Cognizant, where I automate approval and change-management workflows and coordinate cross-functional rollouts end-to-end. This gives me a practical, delivery-focused approach on top of my technical background: I'm as comfortable gathering requirements and managing stakeholder sign-off as I am building the underlying system. What I work on: Computer Vision systems (Facial Recognition, Gesture Recognition, OCR) Deep Learning models using OpenCV and TensorFlow Time-series and sequence modeling (LSTM-based systems) Applied GenAI solutions (RAG pipelines, LLM-powered document intelligence) REST APIs for real-time inference and system integration Representative work includes: A high-accuracy facial recognition system using Siamese Neural Networks A real-time American Sign Language recognition system using spatiotemporal modeling An LLM-powered document intelligence system for querying large document collections I currently collaborate with startups, product teams, and founders who need custom Computer Vision or ML solutions that are reliable and deployment-ready. 📩 If you’re building a product involving images, video, or document automation, feel free to reach out with your use case.

Location

Hyderabad

AI stack

antigravity

claude code

claude

codex

hugging face

Blackbox AI

Work experience

Program Analyst at Cognizant, Jun 2025 - Present · 1 yr 4 mos, Hyderabad, Telangana, India, • Own end-to-end automation of ServiceNow approval workflows for change requests and incidents, coordinating directly with business and engineering stakeholders to secure timely sign-offs. • Plan and execute software upgrade rollouts across multiple production servers — scheduling, validation, and stakeholder communication through each phase of the rollout. • Gather requirements from stakeholders for new features and process changes, then scope and implement the corresponding automation updates. • Write Python scripts to automate repetitive data-transformation and reporting tasks, improving throughput and accuracy of existing workflows.

Computer Vision & Machine Learning Engineer at Freelance, Apr 2023 - Present · 3 yrs 6 mos, Remote, 🔹 LLM-Powered Document Intelligence System Tech: GenAI, LLMs, RAG, FAISS, Python, REST APIs Designed and implemented an end-to-end Retrieval-Augmented Generation (RAG) system for querying large document collections Built document ingestion, chunking, and embedding pipelines using transformer-based models and FAISS vector databases Enabled semantic search and contextual response generation through LLMs Exposed the system via REST APIs for real-time inference and enterprise integration 🔹 Facial Recognition System (Siamese Neural Networks) Tech: Computer Vision, Deep Learning, OpenCV, TensorFlow Developed a high-accuracy facial recognition and verification system using Siamese Neural Networks Engineered face embedding pipelines and similarity-based identity verification logic Optimized preprocessing and model tuning to achieve 98% accuracy Designed the system for real-world identity verification use cases 🔹 American Sign Language (ASL) Recognition System Tech: OpenCV, MediaPipe, LSTM, Time-Series ML Built a real-time ASL gesture recognition system using spatiotemporal hand landmark sequences Applied LSTM-based models for dynamic gesture recognition Achieved 97% accuracy in real-time classification Optimized the pipeline for low-latency inference

Public links

github: https://github.com/aditya-0114