Open to opportunities

Walee Ismail

@waleeismail

Message

I build production Generative AI, RAG, and cloud platforms that automate high-volume business workflows.

United States

Message

What I'm looking for

I'm looking to build secure, scalable production AI systems where I can lead Generative AI architecture, RAG workflows, LLM evaluation, and cloud deployment for high-impact business problems.

I'm building enterprise Generative AI platforms for Prypco, including a cloud-native document intelligence system that processes 1,000+ mortgage applications monthly.

I design secure RAG, LLM orchestration, vector retrieval, validation, and human-in-the-loop workflows for financial automation. My WhatsApp Business API, Slack, and automated decision pipelines reduced mortgage advisor review time by 70%, while Langfuse-based observability tracks latency, cost, model performance, and human-AI agreement.

Previously at EY, I delivered secure AWS-based Generative AI solutions for healthcare, spanning Amazon Bedrock, SageMaker, Lambda, ECS Fargate, Kinesis, Textract, and Terraform/CDK. I helped build LLM applications, AI agents, document intelligence workflows, and clinical summarization systems supporting 50,000+ clinical encounters annually.

Earlier at inDrive, I built Python and Django backend systems for a high-traffic transportation platform, improving ride allocation by 13%, reducing ride duration by 7%, and maintaining 99.9% uptime.

Experience

Work history, roles, and key accomplishments

Current

Senior ML Engineer

Current

Prypco

Oct 2024 - Present (1 year 10 months)

Architected an enterprise Generative AI document intelligence platform using cloud-native AI services, LLM orchestration, RAG workflows, and scalable backend systems to process 1,000+ mortgage applications monthly. Engineered human-in-the-loop AI workflows integrating WhatsApp Business API, Slack, and automated decision pipelines, reducing mortgage advisor review time by 70%.

Data Scientist

Feb 2021 - Oct 2024 (3 years 8 months)

Architected and delivered enterprise-scale Generative AI solutions on AWS, designing secure cloud-native architectures using Amazon Bedrock, SageMaker, Lambda, ECS Fargate, Kinesis, Textract, and Terraform/CDK for healthcare AI transformation initiatives. Led the design of LLM-powered applications including RAG pipelines, AI agents, document intelligence workflows, and clinical summarization syste

AWS Bedrock Sagemaker Lambda AWS ECS Fargate Kinesis Amazon Textract Terraform CDK Generative AI RAG AI Agents Document Intelligence LLM Evaluation Cost Optimization Governance Security Healthcare AI

Software Engineer

Indrive

Sep 2017 - Feb 2021 (3 years 5 months)

Designed and developed scalable cloud-based backend systems for a high-traffic transportation platform using Python, Django, PostgreSQL, Redis, and AWS infrastructure, supporting reliable real-time application workflows. Architected and optimized ride-matching and dispatch systems using Celery, Redis, and PostGIS, reducing ride allocation time by 13% and improving matching efficiency across high-v