Open to opportunities

Maira User

@mairauser2

AI/ML Engineer building LLM systems at Zindigi – JS Bank, including RAG-based internal tools and backend incident workflows.

Pakistan

Message

At Zindigi – JS Bank, I resolved backend incidents through API log analysis and root-cause investigation, and automated troubleshooting with Python scripts.

I also engineered LLM prompts for internal debugging workflows and integrated vector database search into RAG-based internal tools.

At Synergy Computers Pvt. Ltd., I built LLM-powered incident-analysis features and prompt pipelines that generate root-cause summaries from raw logs for a SaaS observability platform.

Earlier, at ITSOLERA, I designed and deployed a LangChain and ChromaDB RAG chatbot serving 500+ daily queries, and deployed a Dockerized inference pipeline on AWS EC2. I also built the FashionFusion3D sketch-to-fashion generation system, including a React Native virtual try-on app.

Experience

Work history, roles, and key accomplishments

AI / Backend Engineer

Synergy Computers Pvt. Ltd.

May 2026 - Sep 2026 (4 months)

Built LLM-powered incident-analysis features for a SaaS observability platform, accelerating root-cause identification for on-call engineers. Designed prompt-engineering pipelines to auto-generate root-cause summaries and operational insights from raw logs.

LLM incident analysis Prompt Engineering Python Dynatrace Observability Backend Data Processing

Technical Backend Engineer

Zindigi – JS Bank

Jan 2026 - Aug 2026 (7 months)

Resolved 50+ backend incidents daily via API log analysis and root-cause investigation, cutting recurring-issue turnaround time. Automated backend troubleshooting workflows with Python scripts and engineered LLM prompts for internal debugging workflows.

API Analysis Root Cause Investigation Python LLM Prompt Engineering Vector Databases RAG Backend Troubleshooting

Generative AI Engineer Intern

ITSOLERA

Jul 2024 - Oct 2024 (3 months)

Designed and deployed a RAG chatbot (LangChain, ChromaDB, FastAPI) handling 500+ daily queries, improving response relevance over a keyword-search baseline. Deployed a Dockerized inference pipeline on AWS EC2 supporting 100+ concurrent users at sub-500ms response latency.

Lang Chain ChromaDB fastAPI RAG Docker EC2 CLIP BERT Text Summarization

AI/ML Engineer Intern

Disruptive AI, National Incubation Center

Jul 2024 - Sep 2024 (2 months)

Built and load-tested a FastAPI RAG chatbot (LangChain, ChromaDB) supporting 100+ concurrent users with low-latency inference. Developed a sketch-to-fashion image generation pipeline (Stable Diffusion + CLIP retrieval), validated through pilot user testing.