abdullah nasir / fde
Forward Deployed Engineer · AI systems

AbdullahNasir.

I build AI systems where there isn't a playbook yet. I find the real problem, architect around the constraints, and think in trade-offs before I think in code.

01What I build on my own

founder sole builder

Orient

Agentic Harness Claude Code, Agent SDK, Node.js

The self-improving AI system that understands you before it builds.

  • It understands before it acts.
    A grounded conversation turns intent, constraints, and taste into a North Star.
  • It separates building from judging.
    Fresh-context agents execute and critique independently against the same intent.
  • It improves from use.
    Every session becomes candidate skills; only improvements that pass evals survive.
How Orient works, in three systems: the orchestration, where you and the orchestrator reach a North Star and delegate the build to fresh Execute and Critique agents that end at your approval; the skills library the agents draw from; and the self-improving foundation, which watches the whole orchestration, sharpens the skills, and files pages into a brain you own.
The Orient system: orchestration, a skills library, and a self-improving foundation.

Don't let the builder grade its own work.

Orient · Plan · Execute · Critique · Approve View on GitHub

Nonprofit platform

web platform 2025

A 1,000+ member community ran its core operations through group chats. I replaced that with one production system for events, membership, and donations.

Next.jsSupabaseTwilioClaudeTypeScript

02What I build at work

client engagements Deloitte

Make it deterministic where the output must be exact. Reach for an agent only where judgment is the real work.

Industrial · 2025–present

Digital twins in NVIDIA Omniverse
  • Sole architect of an agentic engine embedded in NVIDIA Omniverse for designing, simulating, and validating industrial environments.
  • Designed as a reusable engine across industrial domains.
  • Now leading six engineers re-architecting the engine on LangGraph for data-center workflows.
Physical AIOmniverseLangGraph

The leverage is never one magic model. It is model choice plus the workflow around it.

Entertainment · 2026

Generative video pipeline
  • Architected a model-agnostic pipeline turning creative intent into conformed generative assets for downstream production.
  • Built an evaluation framework with studio leadership, scoring 20+ models across six dimensions to turn black-box behavior into defensible decisions.
Generative videoModel evalModular pipeline

A creative problem needs a dedicated reasoner before execution, not just a router.

Animation · 2025

3D scene assembly from intent
  • Led technical discovery to translate artists' open-ended intent into finite 3D scene logic.
  • Rebuilt ChatUSD to run independently of Omniverse in two weeks, working directly with the studio's CTO on their first-ever consulting engagement.
Agentic planningUSDChatUSD

Foundation where the instincts formed

Healthcare · 2025

AWS and GPU infrastructure with Kubernetes microservices behind an NVIDIA ACE patient-intake avatar, tested live with patients on site.

Public sector · 2024–25

Statewide platform infrastructure on AWS.

If this is how you think too,
let's talk.

Email LinkedIn
FounderOrient (open source, MIT)
PubACM DigiPro 2026 co-author
CertClaude Certified Architect
OrgDeloitte, AI & Data
© Abdullah Nasir 2026 · Columbus, OH