Hello, I'm
Marium Ashraf
|
Hello, I'm
|
Get To Know More
3+ years
AI Systems, LLM Engineering & Full-Stack Development
B.Eng. Computer Engineering (Major in Software Engineering)
Toronto Metropolitan University
Graduating April 2027
Vector Institute DaRMoD Cohort (F2025)
I build production-ready AI and data systems that improve how teams operate — reducing operational friction, improving quality, and enabling better decisions.
90% faster operations • 35% better model quality • 60% less debugging time
From RAG pipelines to real-time dashboards, I ship systems teams can reliably use and maintain. Vector Institute trained. Production-focused. Results-driven.
Professional
Vector Institute
Fall 2025
Production ML systems with an emphasis on data readiness, governance, evaluation frameworks, and risk-aware deployment in real operational environments.
Toronto Metropolitan University
Graduating April 2027
Software Engineering major. Software Design. Requirements Analysis. Database Systems. Algorithms & Data Structures.
Key
SOP Lookup Latency Reduction
AI-assisted tooling at Lyrata
Model Outputs Processed Daily
Scalable evaluation pipelines
Onboarding Time Reduction
LyrataGPT SDK-like interface
Explore My
July 2025 – Present
Built LyrataGPT — AI tooling that cut SOP lookup by 90% and onboarding by 50%. Python, Flask, PostgreSQL, ChromaDB, GPT-4o. Vector Institute DaRMoD trained. Production systems teams can reliably use and maintain.
November 2022 – July 2025
Designed and scaled LLM evaluation and quality systems supporting 1,000+ outputs/day, enabling clearer release decisions, faster debugging, and measurable model improvements.
January 2022 – December 2023
Full-stack React apps. Stripe payments. SQL databases. CI/CD with Jest & GitHub Actions. Production features that ship.
Explore My
Python, Java, JavaScript/TypeScript
GPT-4o, RAG, embeddings, MLflow. Vector databases. Evaluation pipelines. 35% model quality improvement.
Docker, microservices, RabbitMQ. Fault-tolerant routing. Real-time observability. SDK design. Slack/Google Sheets integrations.
PostgreSQL, MongoDB, BigQuery, Snowflake. ETL pipelines. Power BI dashboards. SQL observability. 60% faster debugging.
Business & Systems
I specialize in diagnosing ambiguous operational problems, structuring them into measurable workflows, and delivering systems teams actually adopt.
SQL dashboards → Real-time insights. Power BI → Stakeholder reporting. 60% faster root-cause analysis. Data-driven decisions, not guesswork.
BRDs → Technical specs. Process mapping → Automation. Stakeholder workshops → aligned requirements and adoption-ready solutions. DaRMoD-aligned workflows teams can reliably use and maintain.
Translate ambiguity into clear requirements, metrics, and delivery plans. Technical findings → Business language. 30% faster feature delivery through better alignment. Cross-functional collaboration that ships.
Browse My Recent
Quarterly capsule wardrobe planner + “Should I buy this?” AI decision assistant. Plans cohesive wardrobes and scores items for closet overlap, price-per-wear, and review-derived fit/value.
React + Vite + Tailwind frontend, FastAPI backend, SQLite. Capsule generation with real product data, palette extraction, versatility scoring, TTL caching. Evaluation harness skeleton, CI (lint, format, tests). Demonstrates end-to-end product thinking: requirements → scoring logic → evaluation → iteration under real constraints. Demo coming soon.
A FastAPI microservice demonstrating end-to-end observability through Grafana, Prometheus, Tempo, and Loki. Features OpenTelemetry instrumentation for trace-to-log correlation and metric exemplars, deployed via Docker Compose.
Implements trace injection across three FastAPI services using the OpenTelemetry SDK with Prometheus metrics, Tempo tracing, and Loki log pipelines.
Load tested via Locust and k6 to validate distributed tracing and resource efficiency, with metrics visualized in Grafana dashboards for real-time debugging and performance monitoring.
A Streamlit-based analytics app for visualizing Bluecoins expense data using Python, SQL, and Docker. Designed to support intuitive budget tracking and category insights with a responsive, minimal interface.
Developed an ETL pipeline from CSV → SQL → Streamlit UI using pandas and SQLAlchemy, containerized via Docker Compose for reproducibility. Provides dynamic charts on income trends, category flow, and net balance with future integrations planned for OAuth login and hosted deployment.
A serverless financial chatbot that guides users through retirement investment planning. Built with AWS Lex for NLP dialogue management and AWS Lambda for real-time portfolio recommendations based on user risk profiles.
Implements Lambda-backed validation for user intents and secure financial calculations with algorithm-driven portfolio allocation based on risk tolerance and horizon. Built with serverless architecture for scalability and low-cost deployment, featuring an integrated conversational flow designed for accuracy, responsiveness, and ease of use.
Get in Touch
I'm always interested in discussing new opportunities, collaborations, or just having a chat about technology and innovation.
