Abhiram

Ai Engineer

ZS • Full time

Aug 2025 - Present • 11 mos

Designing and deploying RAG (Retrieval-Augmented Generation) pipelines for enterprise knowledge retrieval and document understanding. Building single-agent and multi-agent AI systems using LangChain and LangGraph to automate compliance, legal, language quality, nomenclature, and content validation workflows. Developing OCR and document intelligence pipelines using YOLO, PaddleOCR, Tesseract OCR, and AWS Textract to extract structured information from complex scientific and medical documents. Building scalable FastAPI microservices and REST APIs for AI applications and integrating them with enterprise platforms such as Veeva Vault. Developing semantic search and similarity analysis solutions for claim validation, auto-referencing, and content reuse detection using vector databases and embedding models. Deploying and managing AI workloads on AWS using EC2, S3, ECR, Batch, RDS, CloudWatch, and Airflow while following production-grade MLOps and deployment practices. Working across the complete AI solution lifecycle, including requirement analysis, model development, prompt engineering, evaluation, deployment, monitoring, and optimization. Collaborating with cross-functional teams to deliver scalable, enterprise-ready AI solutions that significantly reduce manual effort and improve operational efficiency.