Open to opportunities

Ganga Babu

@gangababu

Message

Senior AI Engineer building scalable GenAI infrastructure—LLM, RAG, and agents—for reliable, cost-optimized SaaS.

India

Message

What I'm looking for

I’m looking for a role where I can own production GenAI systems end-to-end—designing multi-tenant, observable, cost-optimized LLM/RAG pipelines—and collaborate to ship reliable automation that improves enterprise document workflows.

I’m a Senior AI Engineer focused on scalable GenAI infrastructure for SaaS enterprise document intelligence, with 6+ years architecting production-grade systems. I lead end-to-end delivery across LLM, RAG, and autonomous agent workflows, emphasizing reliability, observability, and cost control.

My work has delivered measurable impact, including an 83.78% reduction in operational costs through LLM routing and pipeline LLMs, RAG architectures, and autonomous agent optimization. I also improved latency by 78% while stabilizing migrations—from legacy retrieval/storage backends to a mono-repo architecture—under live enterprise load.

I build multi-tenant, asynchronous processing pipelines for large-scale document workflows, including OCR and object detection (with custom YOLO). Using Azure and AWS services, plus strong failure recovery and retry mechanisms, I turn research-driven experimentation into production-ready AI platforms.

Experience

Work history, roles, and key accomplishments

Current

Senior AI Engineer

Current

Nuvento Inc

Jul 2022 - Present (3 years 10 months)

Led stabilization and migration of an AI document processing platform to a monorepo architecture under live production load. Implemented LLM routing and optimization strategies that reduced document processing costs by 83.78% and improved latency by 78%.

RAG Celery Redis Async Pipelines Azure Functions Prompt Engineering Observability

Software Developer (ML/AI)

IT Solutions Pvt. Ltd

Aug 2021 - Jul 2022 (11 months)

Developed computer vision–based OCR systems for automated text extraction and built ML-based prediction components for real-time analytics workflows. Trained custom YOLO models for document classification and detection and designed preprocessing/feature engineering pipelines for model training and inference.

Computer Vision YOLO Training Real Time Analytics Model Inference Model Training Python TensorFlow PyTorch

Jr. Provisioning & Configuration

Tata Communications

Jan 2018 - Aug 2021 (3 years 7 months)

Managed global circuit provisioning and migration processes across UK and international regions. Built an NLP-based internal analytics tool to automate audit reporting and partnered with operations and engineering to streamline execution.

Network Provisioning Circuit Migration NLP Audit Reporting Data Analysis Reporting Compliance Support

Education

Degrees, certifications, and relevant coursework

Great Lakes Institute of Management, Chennai

Postgraduate Program in Artificial Intelligence and Machine Learning, Artificial Intelligence and Machine Learning

2019 - 2021

Postgraduate program in Artificial Intelligence and Machine Learning completed from 2019 to 2021. Studied AI and ML fundamentals through an industry-focused executive program.