A bilingual Arabic/English system for repair shops to manage devices from intake to delivery.
roleProduct planning, research, architecture, implementation, verification, deployment, and documentation
Read case studyAI Engineer based in Gaza, working remotely
I build AI workflows and the systems that keep them useful in production.
I work on GAITH at OSOS, where I develop AI features and integrations, research technical options, plan work, review changes, and debug issues across the platform. My background combines software verification, production systems, and practical AI-assisted engineering.
projects
Selected work
Machine-learning models that ranked lighting-pole maintenance priorities from condition data.
roleSoftware Engineer
Read case studyAn on-demand water-delivery system connecting customers with water-truck drivers.
roleTeam planning, communication, and development
Read case studyexperience
Professional experience
AI Engineer
OSOS
I work on GAITH, OSOS's AI orchestration platform. My role covers feature development, technical research, planning, Jira coordination, debugging, code review, testing, and release support.
- Developed AI features, workflows, and integrations for GAITH, OSOS's AI orchestration platform.
- Researched new features and technical options and contributed to design and implementation plans.
- Created and assigned Jira tasks, clarified requirements, and coordinated delivery with the team.
- Traced and fixed platform issues, reviewed pull requests, and added tests to prevent regressions.
Software Verification Engineer
NVIDIA Firmware Tools Team | Unit One Group
Worked on software verification for NVIDIA firmware tools used with switches and network interface cards. Maintained Python regression tests, investigated failures, tested releases, wrote test plans, and worked with verification, QA, and engineering teams.
Teaching Assistant
Islamic University of Gaza
Taught Data Structures and Algorithms in Java to about 90 students, covering core data structures, recursion, and time and space complexity.
approach
How I work
Research before implementation
I read the existing system and compare technical options before committing to a design. The current code and documented behavior are the starting point.
Plan work so others can act on it
I turn decisions into scoped tasks, clarify requirements, and keep implementation and review work easy to follow.
Use agents with engineering controls
I use Claude Code, Codex, MCP, skills, hooks, memory, and worktrees, but I keep tests, review, and acceptance criteria outside the model's judgment.
Stay with problems through debugging
I trace issues across services, logs, state, and integrations, then add tests or safeguards so the same failure is easier to catch next time.
skills
Technical areas
Grouped by where I use these tools, not as a flat badge list.
Primary languages
Python and Java are my strongest languages. I use them for backend services, verification tooling, and AI workflows.
Project and working experience
Backend and data
I build Python services with FastAPI, Celery, Redis, PostgreSQL, and pgvector. These show up in production AI systems and personal projects.
AI and knowledge systems
I work with LLM applications, RAG, embeddings, document ingestion, and knowledge-base indexing in production contexts.
Microsoft integrations and identity
OAuth/OIDC, SSO, multitenancy, role-based permissions, and tenant isolation come up in platform integration work.
AI agent tooling
I use Claude Code, Codex, MCP, custom skills, hooks, and multi-agent workflows as engineering tools with review gates and structured handoffs.
Verification and quality
My verification background shapes how I approach testing, regression prevention, and release validation.
DevOps and platforms
Docker, CI/CD, Kubernetes, and Linux operations support the systems I build and maintain.
background
About
I am a software engineer who moved from verification into production AI engineering. I like work that starts as an unclear problem and ends as a tested, maintainable system. That usually means reading the existing code, researching options, turning the decision into tasks, helping with implementation, and staying with the change through review and debugging.
I also work deeply with Claude Code, Codex, MCP, agent memory, custom skills, hooks, and multi-agent workflows. I use those tools to speed up engineering work, but not to replace judgment. Tests, review, and clear acceptance criteria remain the gate.
Before OSOS, I worked on NVIDIA firmware-tools verification and taught Data Structures and Algorithms in Java at the Islamic University of Gaza.
get in touch
Contact
Email is the best way to reach me for questions, collaboration, or to request a CV:alhasan.ahmad.alkhatib@gmail.com