Portrait of Syed Waleed Ahmed

hi, Waleed here.

I build multi-agent systems, RAG pipelines, and LLM workflow automation.

My focus is the work most demos leave out: evaluation, observability, and the engineering that turns a working prototype into something a team can rely on every day.

Graduated from the University of Bologna in October 2026 with a Master's in Automation Engineering and a thesis built at MemorAIz S.r.l. Now open to AI and ML engineering roles.

View projectsResume

About

Half full-stack engineer, half AI/ML. How I got here, and what I'm looking for next.

  • 985Automated tests across the thesis service, its console and its first tenantRemindrAI
  • 97.5%Item-match accuracy across six supermarket chains, against a 95% targetFruugle
  • 99.5%Product-category accuracy across 16 classesFruugle
  • 100K+Records moved through ETL pipelinesJubilee Life Insurance

Approach

I build models the way I would build any other production service: real APIs, error handling, observability. The alternative is a notebook that runs beautifully on my laptop and nowhere else, and I have written enough of those to know better.

A year rotating through cybersecurity, web development, and database administration means I can hand over a whole working system, rather than the ML half and a hopeful note about deployment.

Most of the work goes on the unglamorous part: retries, idempotency, and whatever decides to fail at three in the morning. Nobody puts that in the demo. It is usually the reason the demo still works next week.

Education

  1. Master's in Automation Engineering

    Alma Mater Studiorum - Università di Bologna, Italy

    Oct 2024 - Oct 2026

  2. Erasmus+ Mobility

    University of Twente, Enschede, Netherlands

    Sep 2025 - Jan 2026

  3. Bachelor's in Electrical Engineering

    NED University of Engineering and Technology, Karachi, Pakistan

    Oct 2019 - Aug 2023

Roles I'm targeting

AI Engineer
Agents, tool use, and the infrastructure that makes them dependable.
ML Engineer
Models trained, evaluated, and served like any other production service.
Full-Stack AI Engineer
End to end: the model, the API, and the interface it is served through.

Experience

The roles I've held and the systems I built in each one.

  1. Feb 2026 - Oct 2026

    Bologna, Italy

    AI Engineer · Master's Thesis

    MemorAIz S.r.l.

    • Built RemindrAI for my thesis: a multi-tenant reminder backend, its operator console, and the Mastra capability other AI assistants register in one line.
    • Made delivery retry-safe with an atomic database claim, per-channel idempotency, and database-owned backoff; median claim latency stayed near-flat from 1K to 100K due reminders.
    • Engineered the control plane: per-organization API keys, tenant isolation at four independent depths, plans and quotas as data, and audited GDPR export and erasure.
    • Shipped EU-pinned on Vercel under 985 tests across three repositories, with H-FARM's Student Assistant as the first production tenant.

  2. Jan 2026 - Apr 2026

    Jelgava, Latvia (Remote)

    Data Clustering & AI Model Intern

    Fruugle SIA

    • Built an XGBoost model that matches the same grocery item across 6 Italian supermarket chains, reaching 97.5% accuracy against a 95% target.
    • Trained a second model to classify products into 16 categories at 99.5% accuracy, using class weighting so under-represented classes were not ignored.
    • Engineered the pipeline over 80K+ scraped products: Italian-text cleaning, a quantity parser, and hard-negative sampling for ambiguous pairs.
    • Wrote an inference script that grouped 24K+ unsorted products, with guardrails to reject implausible matches.

  3. Jan 2024 - Oct 2024

    Karachi, Pakistan

    Tech Trainee

    Jubilee Life Insurance Co. Ltd.

    • Rotated through web development, databases, networking, and cybersecurity, building full-stack applications with React, ASP.NET Core, PHP, and MySQL.
    • Built ETL pipelines over 100K+ records and tuned queries and stored procedures, cutting database response times by ~40%.
    • Automated SharePoint and CRM workflows for internal teams, reducing manual effort by ~60% and speeding up client response.
    • Monitored threats on IBM QRadar (SIEM/SOAR/PAM) and delivered 15+ SSRS reports and Power BI dashboards for business analytics.

Selected projects

Thesis, independent and university work across applied AI and robotics. Source code is linked wherever the repository is public.

  • Master's Thesis · MemorAIz S.r.l.

    RemindrAI: Embeddable Multi-Tenant Reminder Capability

    A reminder and messaging service that AI assistants embed instead of rebuilding. An agent turns plain chat into reminders delivered over Email, WhatsApp, Telegram, and Discord, and each reminder's owner is pinned outside the model, so a prompt injection cannot retarget it.

    Its first tenant adopted it with a base URL and a token, holding no scheduler, queue, or provider secret.

    • Next.js 16
    • TypeScript
    • Vercel AI SDK
    • Mastra
    • Turso / libSQL

    Private repository · MemorAIz

  • Robotics Project · Master's · Team of 3

    TIAGo: Autonomous Mapping, Navigation & Pick-and-Place

    A TIAGo mobile manipulator that maps an unknown indoor space on its own, then recovers where it is from a random start pose, finds two workstations by their ArUco markers, and carries two cubes between them in a required order. It runs end to end with no teleoperation, one launch command per task.

    No map coordinates in the source: every station and cube pose is discovered from markers at runtime, so the mission moves to a new world unchanged.

    • ROS 2 Humble
    • Nav2 / SLAM
    • ArUco
    • Gazebo
    • Python
    View source

  • Independent Project

    Campaign Forge: Multi-Agent Marketing Workflow

    A multi-agent pipeline that turns a one-line product brief into a campaign ready to hand off. Research, copywriter, art-director and manager agents each own one stage, running on any OpenAI-compatible endpoint with Groq as the default.

    Retries with backoff, Pydantic-validated output and a self-repairing JSON step, backed by 94% test coverage and an adversarial eval corpus.

    • Python
    • OpenAI SDK
    • Groq
    • Pydantic
    • pytest
    View source

  • Independent Project

    Self-Correcting RAG Pipeline

    A RAG pipeline that checks its own work. A guardrail agent scores each retrieved chunk and drops off-topic context, then an evaluator grades the answer against its sources and triggers a bounded correction loop when grounding is weak.

    Keeps the best-scoring attempt, so a correction never regresses an answer. Served as a FastAPI service and a CLI, with 31 offline tests.

    • Python
    • FastAPI
    • sentence-transformers
    • FAISS
    • Groq
    View source

  • Course Project · Master's

    Visual Inspection of Motorcycle Connecting Rods

    A classical computer-vision pipeline that inspects connecting rods from grayscale images. It tells the two rod types apart by hole count, then measures each rod's position, orientation, length and width, and every hole's center and diameter.

    Extended to cope with distractor objects and scattered iron powder, using Gaussian and bilateral filtering and area-filtered connected components.

    • Python
    • OpenCV
    • NumPy
    • SciPy
    View source

  • Bachelor's Thesis

    Delay Classification for Tele-Robotic Systems

    A time-series and ML pipeline that classifies network delay across LAN, WAN, and 4G environments. Built from captured latency traces, it flags the conditions that would destabilize a remote tele-robotic control loop before they cause failures.

    ~25% improvement in control-loop stability under variable network conditions.

    • Signal Processing
    • TCP/IP
    • UDP
    • Networking
    • C++

    No public repository

Skills

The tools and frameworks I work with, grouped by where they apply.

AI / LLM Engineering
  • Multi-Agent Systems
  • RAG
  • Prompt Engineering
  • Fine-tuning
  • Mastra
  • Vercel AI SDK
  • LangChain
  • LangGraph
  • Hugging Face
  • OpenAI
  • Groq
ML & Data
  • PyTorch
  • TensorFlow
  • scikit-learn
  • XGBoost
  • OpenCV
  • Pandas
  • NumPy
  • Matplotlib
  • Seaborn
  • Statistical Analysis
  • Power BI
Languages
  • Python
  • TypeScript
  • JavaScript
  • SQL
  • C++
Web & Backend
  • React
  • Next.js
  • Server Components
  • Node.js
  • ASP.NET Core
  • REST APIs
  • Serverless
  • Multi-Tenancy
  • Webhooks
  • Vitest
Data & Messaging
  • PostgreSQL
  • MySQL
  • SQL Server
  • MongoDB
  • Turso / libSQL
  • pgvector
  • Drizzle ORM
  • Redis
  • Kafka
  • Upstash QStash
  • Twilio
Cloud & DevOps
  • AWS
  • Vercel
  • Docker
  • Kubernetes
  • Terraform
  • CI/CD
  • Linux

Contact

Whether it's a role, a question, or a collaboration, send a message. I read every one.

All fields are required.