Open to opportunities

Mohd Imran Shountoo

@mohdimranshountoo

Message

Applied AI Engineer building LLM-powered, distributed backend systems that cut validation and processing time fast.

India

Message

What I'm looking for

I’m looking for a role where I can build production-grade LLM and AI systems—event-driven backends, RAG pipelines, and real-time apps—while owning architecture, observability, and performance improvements from prototype to deployment.

I’m an Applied AI Engineer focused on turning LLM and AI workflows into reliable, production-ready systems. Since Feb 2024, I’ve built end-to-end solutions using OpenAI API, Gemini API, and RAG pipelines to deliver measurable time savings.

My work centers on architecture and performance: I designed an event-driven, fault-tolerant pipeline on AWS (Lambda, SQS, S3) with microservices and dead-letter queues, orchestrating multi-staged document analysis. I also optimized large PDF processing (100+ pages) with parallel page-level jobs to improve throughput and avoid Lambda timeouts.

I build interactive and scalable applications too—like a real-time AI chatbot with OpenAI APIs and Socket.IO, and AI platforms for construction plan and HVAC estimation. I’m comfortable across the stack (Node.js/Express.js/NestJS/FastAPI/GraphQL, React/Next.js/React Native) and in the tooling that makes AI observable and debuggable (Langfuse, pipeline tracing, CI/CD).

Experience

Work history, roles, and key accomplishments

Current

Applied AI Engineer

Current

Saibbyweb

Feb 2024 - Present (2 years 4 months)

Built distributed AI processing systems using AWS Lambda, SQS, and microservices for multi-staged document analysis, improving throughput by parallelizing 100+ page PDFs. Developed AI backends/frontends that cut construction plan validation time from 1–3 weeks to ~4 hours (~90%) and scaled a multilingual speech-to-speech app to 200K+ users within two weeks.