user1400886

AI Engineer at AT&T

Engineered a transformation pipeline to convert raw landing content into PDF, apply metadata tagging, and securely store artifacts in Azure Data Lake Storage. Developed a text understanding and intent-detection system using few-shot prompting and retrieval-augmented generation (RAG). Automated analysis of customer service transcripts to extract key intents, issue categories, sentiment, and resolution status, converting outputs to structured JSON. Integrated an LLM-driven module to translate user questions into valid MongoDB queries with filters and aggregations. Applied prompt chaining, output parsing, and token filtering; collaborated with frontend/backend teams to expose AI APIs. Implemented data privacy measures including PII masking and secure API communications.

AI Engineer at AXA XL

RAG-based architecture project to extract attributes from PDFs stored on Azure; chunked documents, designed similarity scoring, and GPT-based LLM prompts for multi-attribute extraction. Built data pipelines to preprocess structured/unstructured data, performed model fine-tuning, and crafted prompts to improve extraction accuracy. Exposed results via REST APIs and integrated with existing tech stacks.

AI Engineer at AXA XL

Table Detection and Content Extraction: Developed deep learning models for table detection and integrated Azure Document AI to handle complex structures (bordered/borderless/merged/implicit tables) in noisy documents. Implemented OCR and layout analysis, edge-case handling, and pre/post-processing pipelines. Deployed containerized solutions with Docker and Kubernetes for production use.

AI Engineer at AXA XL

Human-in-the-Loop Evaluation Metric for AI Systems: Designed a metric combining log probabilities, top-k token predictions, and model uncertainty to assess AI outputs without ground truth. Built a framework to incorporate human feedback, validated across AI workflows, and documented for scalability and real-time monitoring integration.

Data Engineer / Data Scientist / Machine Learning at Intellect Design Arena

Led NLP-powered automation for loan applications: built ETL processes using SAS for demographics and historical default analysis; analyzed data with R for feature engineering; trained XGBoost for credit risk with ensemble averaging. Automated NLP data extraction and leveraged Retrieval-Augmented Generation (RAG) with LLMs (LLM-BERT) for structured extraction. Implemented CI/CD with GitLab, containerized with Docker/Kubernetes, and deployed APIs via FastAPI. Worked on identity-card extraction and signature verification modules; developed dashboards and integrated Azure/GCP for scalable deployment.

Algorithm Engineer at Carl Zeiss

Developed and optimized SurfMax defect-detection algorithms for automated surface inspection across various materials. Evaluated repeatability and objectivity against traditional methods, configured SurfMax per sample, and built training/validation datasets to support defect detection. Created visualizations and reports in Python to communicate results and supported data quality improvements and process optimization.

Computer Vision Engineer at Revealix

Thermal analysis using semantic segmentation for diabetic patients: captured real-time limb temperature data with a FLIR camera, labeled dataset, and trained a segmentation model to isolate regions for cold/hot spot analysis. Integrated segmentation with the thermal-imaging workflow, implemented ETL for data management, and developed a web-based visual interface for real-time results. Ensured HIPAA/regulatory considerations and containerized workflows with Docker.