.png&w=256&q=75)
4
2
Algeria
3+ years of experience
AI/ML Engineer and Full-Stack Developer currently pursuing a Master’s degree in Artificial Intelligence. I build practical AI-powered applications and full-stack products using Python, JavaScript, Node.js, Express.js, MongoDB, PHP, Laravel, Flutter, and REST APIs. I enjoy turning ideas into working products, with a focus on AI engineering, automation, backend systems, and intelligent applications. I’m especially interested in building and experimenting with AI agents, machine learning, and generative AI. Currently looking to collaborate with technical builders, participate in AI hackathons, and build impactful real-world projects.

Bob Debug Pipeline is an AI-assisted developer workflow built around IBM Bob 2.0 that helps developers turn a failing test into an understood, validated fix. The problem we address is a common but time-consuming debugging workflow: developers must inspect failing tests, trace the underlying implementation, identify the root cause, determine the expected behavior, create or validate a regression test, implement a fix, and verify that the change does not break existing functionality. These steps can require repeated manual investigation and context switching. Our MVP demonstrates this workflow using a concrete Jest debugging scenario. The test project contains a getUserById(999) case where the test expects null, but the implementation returns undefined. IBM Bob investigates the relevant files, analyzes the failing behavior, identifies that JavaScript Array.find() returns undefined when no matching element is found, and determines that the implementation does not satisfy the test contract. The proposed minimal fix normalizes the missing result to null. IBM Bob then implements the fix in the relevant service file and runs the focused Jest test. The final validation confirms that both tests pass. We built a React/Vite frontend connected to an Express/TypeScript backend to present the workflow as a clear developer tool. Users can see the bug scenario, root-cause analysis, regression test, generated fix, validation result, and the next GitHub workflow step in one interface. The target users are developers who regularly debug failing tests and maintain existing codebases. The creative aspect of the project is combining IBM Bob's repository-aware investigation and implementation capabilities with a structured debugging pipeline that makes each stage visible and verifiable. The prototype demonstrates a practical workflow from failing test to validated fix, while keeping the debugging process understandable and reproducible.
27 Sep 2026

Intelligent Packing Assistant is a voice-driven robotic packing prototype built by Team 15 for the Intel Bimanual VLA Manipulation with Multi-Modal Reasoning track. The system demonstrates how a natural-language packing instruction can be transformed into structured and executable robot actions. A user provides a spoken instruction, Speechmatics performs real-time speech-to-text, and the resulting instruction is processed by our Python/FastAPI backend. The backend extracts the relevant packing constraints and generates a structured packing plan. For the MVP scenario, the system works with three object types: Heavy, Normal, and Fragile. The generated plan explicitly assigns robotic actions and arms: the Heavy object uses a coordinated bimanual pick-and-place action with arm1 and arm2, while Normal and Fragile are handled by individual arms. The structured plan is exposed through a deployed FastAPI service on Render and connected to a Three.js simulation. The simulator visualizes the robot execution and demonstrates the coordinated two-arm manipulation required by the challenge. The demonstrated workflow is: Voice Command → Speech-to-Text → Instruction Understanding → Packing Plan → Robot Actions → Bimanual Execution → Final Placement The project focuses on building a practical end-to-end prototype that combines voice interaction, structured task planning, backend APIs, and robotic simulation within a modern AI infrastructure workflow.
16 Sep 2026