AI Engineer with 3+ years in RAG & Computer Vision
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI/ML Engineer with around 3 years of experience building production AI systems across Retrieval-Augmented Generation (RAG), multi-agent workflows, and computer vision (CV)/OCR pipelines. Skilled in developing scalable Python/FastAPI microservices, hybrid retrieval architectures, and document-intelligence solutions integrating large language models (LLMs) with vector search.
College of Engineering Trivandrum, Kerala
Master of Technology · Financial Engineering
June 1, 2023 – June 1, 2023
Sree Chithra Thirunal College of Engineering, Trivandrum Kerala
Bachelor of Technology · Electronics and Communication Engineering
October 1, 2019 – October 1, 2019
Ospyn Technologies
AI Engineer
April 1, 2025 – Present
India
Ospyn Technologies
Associate AI Engineer
June 1, 2024 – March 1, 2025
India
College of Engineering Trivandrum, Kerala
Guest Lecturer on Data Analytics, Science and Statistics
August 1, 2023 – June 1, 2025
India
Agentic AI Customer Support Automation Platform
June 1, 2023 – Present
Designed an AI-driven customer support automation platform that resolves user issues by retrieving knowledge base information using vector search, analyzing screenshots and uploaded documents using vision and document intelligence models, and executing agentic workflows powered by Azure OpenAI with human-in-the-loop escalation for complex cases.
Automated Invoice-PO Matching System
June 1, 2023 – Present
Built an AI pipeline that ingests invoice documents from Kafka, extracts structured data using Computer Vision + OCR and automatically matches them with Purchase Orders to detect discrepancies in amount, quantity, and vendor details.
Oriento - Document Orientation Correction Package
June 1, 2023 – Present
Developed a lightweight Python package that automatically detects and corrects text document(in multiple languages) orientation using OCR bounding boxes, enabling reliable preprocessing for document AI pipelines with configurable confidence and angle tolerance parameters.
View ProjectAI Powered multi-agent medical triage system
June 1, 2023 – Present
Developed multi-agent medical triage system using LangGraph, orchestrating specialized agents (data collector, rule-engine agent, triage-reasoner agent) with shared state, deterministic guards, and safe handoff logic
Multi-Level Document RAG Search System
June 1, 2023 – Present
Devised a production-grade RAG pipeline that preprocesses structured documents into multi-granular chunks, embeds and indexes them in Azure AI Search, and uses hybrid retrieval (BM25 + vector) with GPT-40 to deliver accurate, context-aware answers for complex domain queries.
Master's Program -Data Scientist: Simplilearn Certified in collaboration with IBM – 2024
Simplilearn/IBM
January 1, 2024 – Present
Cultural Fit Analysis
The candidate's project portfolio demonstrates a diverse range of AI applications, from customer support automation to medical triage and financial document processing, indicating adaptability and a broad interest in applying AI to different domains. The experience with various cloud platforms (Azure, AWS) and CI/CD tools (Gitlab CI/CD) suggests a modern development mindset. The role as a Guest Lecturer also points to a willingness to share knowledge and contribute to a learning environment. The projects align well with an AI Engineer role, showcasing a proactive approach to building and deploying advanced AI solutions.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a strong problem-solving aptitude and an ability to translate complex AI concepts into practical, deployable solutions. The experience as a Guest Lecturer suggests good communication skills and an ability to explain technical concepts, which is beneficial for team collaboration and knowledge sharing. The focus on production-grade systems implies an understanding of operational requirements and reliability.