AI Engineer building production AI systems.

I build production AI and full-stack systems, contribute to robotics and computer vision, and engineer research pipelines for evaluation and reproducibility.

10+ production systems80+ deployed projects4 merged OSS fixes216-run evaluation pipeline

Engineering Experience

Founder / AI Engineer · August 2025 - Present

Nexasity AI logo

Nexasity AI

Own system architecture, AI/ML integration, deployment, monitoring and client-facing delivery.

Nexasity AI: 10+ AI systems shipped, 10,000+ registered users and 37,000+ monthly requests reported across the portfolio. Grew the engineering team from one to three people. These are organization-level figures, not per-project benchmarks.

ArchitectureAI/ML integrationDeployment & monitoringClient delivery
Visit Nexasity AI ↗

Senior Member, Operations Sub-Team · January 2024 - Present

BRACU Duburi logo

BRACU Duburi AUV

Laptop monitoring beside a swimming pool during Duburi testing
BRACU Duburi · Poolside testing

Contribute to team-built underwater perception, tracking and vision-guided alignment, alongside operations and coordination.

Dataset collection, YOLO detector training, ROS2 and NVIDIA Jetson Orin Nano. Duburi AI Vision and Duburi Simulator are deployed, with live evaluation and validation completed. Earlier recorded simulator checks: 8/8 structural tests for an eight-thruster ROS 2/Gazebo AUV.

Computer visionRoboticsOperations

Course Tester · August 2026 - Present

DeepLearning.AI logo

DeepLearning.AI

Test pre-release AI/ML code exercises, hands-on labs and learning content. Reproduce failures, check edge cases and provide structured technical defect reports.

Reproduce failures, validate edge cases and report technical defects in pre-release code and labs.

Failure reproductionEdge casesTechnical QA

Flagship Systems

SupportGuard approval queue and evidence-backed support decisions

Production support system · Deployed

SupportGuard

Designed a support workflow that grounds answers in approved knowledge and routes risky decisions to human review.

RAGPostgreSQL / pgvectorHuman escalation
skeletree repository scan and context-map output

Production developer tooling · PyPI

skeletree

Published repository context tooling that gives coding agents dependency graphs, directory trees and code signatures.

Pythontree-sitterMCPGitHub Actions
whyLayer decision workflow interface

Production decision system · Deployed

whyLayer

Architected a multi-provider decision workflow that combines adaptive questions, web evidence and confidence-scored verdicts.

FastAPIReact 19TypeScriptSQLite
MarkLens research cover

Production research infrastructure · Released

MarkLens

Designed a reproducible data pipeline to compare how different managers value the same private-credit loan on the same date.

SEC EDGAREntity matchingStatistical validation

Research Engineering

Apart Research · Digital Minds research

Apart Research logo

216-run LLM evaluation pipeline

Implemented and executed 216 runs across 12 matched tasks, two models and three elicitation conditions. Compared model self-reports with deterministic tool-execution logs.

Claude Haiku 4.5 access-report fidelity: 96.5% → 57.6% under structured provenance. Blinded-judgment agreement: Cohen’s κ = 0.98.

Deterministic scoringExperiment orchestrationProvenance

MarkLens · Figures Maker

Reproducible data and research outputs

Implemented the MarkLens extraction, matching and statistical analysis pipeline. Figures Maker produces deterministic PNG, SVG and PDF research figures.

251,350 holdings; 2,163 matched facility-quarters. Figures Maker’s recorded checks include nine tests and 17 subtests.

ReproducibilityData pipelinesDeterministic rendering
MarkLens release ↗

False Containment · AI incident verification

Apart Research logo

192 verifier judgments

Designed the end-to-end evaluation pipeline, constructed controlled evidence-ablation conditions and compared verifier decisions with known incident ground truth.

192 verifier judgments. Operationalized False Containment Rate to measure unresolved incidents classified as resolved under incomplete telemetry.

TelemetryEvidence pipelinesValidation infrastructure

Open Source

Two merged upstream fixes

Grafana logo

Grafana

Fixed multi-value template-variable regex interpolation in the Pyroscope data-source plugin. Resolved the Prometheus Both query-type panel-editor crash.

Both fixes merged upstream.

DebuggingData-source integration

Open-Source Contributor · October 2026

StampyAI / AI Safety Info logo

StampyAI / Alignment Research Dataset

Open-source contributor to StampyAI / Alignment Research Dataset.

Open sourceAI alignment

Two merged upstream fixes

Crawl4AI logo

Crawl4AI

Fixed Markdown export corruption affecting heading hierarchy and table structure. Resolved a WSL browser hang caused by a system proxy conflict.

Both fixes merged upstream.

Markdown correctnessRuntime debugging

Technical Contributor · September 2026

EquiStamp logo

EquiStamp

Technical contributor at EquiStamp.

Technical collaboration

Production Systems Archive

80+ deployed systems across AI/ML, LLMs, robotics, developer tools, research infrastructure, and full-stack applications.

Interested in working together?

Open to AI Engineering and Research Engineering opportunities.
Dhaka, Bangladesh

Find all the hidden AI systems

© 2026 Daud Ibrahim Hassan
hi!
Wish saved.
Take your time. There are ideas, stories, and a few tiny surprises tucked around here.

{{ welcomeSubEls }}

{{ welcomeTitleLine1Els }}
{{ welcomeTitleLine2Els }}

{{ stickyHint }}

AI Engineer building production AI systems.

I build production AI and full-stack systems, contribute to robotics and computer vision, and engineer research pipelines for evaluation and reproducibility.

10+ production systems80+ deployed projects4 merged OSS fixes216-run evaluation pipeline

{{ group.title }}

{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗
{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗

{{ group.title }}

{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}

{{ group.title }}

{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗
{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗

Production Systems Archive

80+ deployed systems across AI/ML, LLMs, robotics, developer tools, research infrastructure, and full-stack applications.

Projects

A few systems, experiments and research projects I have built.

{{ p.title }}

Coming soon {{ tag }}

{{ p.blurb }}

{{ p.stackText }}

{{ p.resultText }}

{{ p.roleLabel }} {{ p.ctaLabel }}

{{ p.title }}

Coming soon {{ tag }}

{{ p.blurb }}

{{ p.stackText }}

{{ p.resultText }}

{{ p.roleLabel }} {{ p.ctaLabel }}

{{ group.title }}

{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗
{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗

{{ archiveCount }}

{{ group.title }}

{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗
{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗

Selected Experiments

Experiments, side quests and things I made to understand how a system works.

What I bring to the table

I build AI agents, RAG systems and voice workflows, with full-stack interfaces, evaluation checks and human approval where the workflow needs it.

{{ skill.label }}

Learn more about me!

Complex systems are my playground, useful software is my goal.

I'm an AI systems engineer and founder of Nexasity AI. I build software that connects models to real workflows, from retrieval and APIs to review interfaces and voice integrations. Projects like SupportGuard and DocOps Approval Agent reflect how I work: make the system useful, keep its decisions inspectable and give people control over risky actions.

Daud Ibrahim Hassan on a sunny coastal pier
{{ photoTooltip.text }}
{{ wordPopCaption }}

{{ researchProfileTitle }}

{{ researchProfileSubtitle }}

50+ volunteer hosts100+ students mentoredSeven hackathons200+ students

{{ group.title }}

{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗
{{ entry.coverAlt }}

{{ entry.meta }}

{{ organizationLogo.alt }}

{{ entry.title }}

{{ entry.photoAlt }}
{{ entry.photoCaption }}

{{ entry.copy }}

{{ entry.detail }}

{{ tag }}
{{ entry.link }}GitHub ↗Live website ↗

{{ tableHintText }}

{{ ts.label }}

Skills

{{ tok.text }}{{ c.ch }}

{{ sk.label }}

Journey

Latest milestones first, by recorded start year and month where available. Club dates are year-only; ongoing roles overlap.

Dated sprints and ongoing activities · 2021 - Present

{{ event.groupTitle }}

{{ event.number }}

{{ event.date }}

{{ organizationLogo.alt }}

{{ event.title }}

{{ event.photoAlt }}
{{ event.photoCaption }}

{{ event.org }} · {{ event.role }}

{{ event.copy }}

{{ clubEvent.date }}

{{ clubEvent.title }} ↗
{{ event.link }}
{{ tag }}
{{ t }}

{{ caseTitle }}

{{ caseSubtitle }}

GitHub ↗ Live website ↗

Role

{{ caseRole }}

Impact

{{ caseImpact }}

Overview

{{ caseOverview }}

{{ section.title }}

{{ section.copy }}

{{ section.diagram }}
{{ link.label }}

Problem

{{ caseProblemIntro }}

  • {{ pt }}

The Opportunity

{{ caseOpportunity }}

Scope & Reach

{{ sc.label }}

{{ sc.value }}

What I owned

  • {{ o }}

Color System

{{ col.label }}

{{ it.title }}

{{ it.desc }}

{{ col.text }}

Objectives → Design framing

{{ ob.goal }}

{{ ob.question }}

Workflow Efficiency

{{ line }}

Designers could now…

{{ line }}

Key constraints & tradeoffs

{{ c.label }} → {{ c.response }}

Research inputs

  • {{ r }}
{{ im.insight }} → {{ im.implication }}

{{ caseObservationsHeading }}

{{ caseObservationsLeftLabel }}

{{ blk.heading }}

  • {{ line }}

{{ blk.text }}

{{ caseObservationsRightLabel }}

{{ blk.heading }}

  • {{ line }}

{{ blk.text }}

How objectives translated to features

Why?

{{ caseSolutionActive.copy }}

{{ caseSolutionActive.listLabel }}

  • {{ tr }}

{{ caseSolutionActive.paragraphLabel }}

{{ caseSolutionActive.thinking }}

KPIs & measurement strategy

{{ k.label }}

Why this mattered
{{ k.why }}

What was measured

  • {{ w }}

Why this was chosen
{{ k.reason }}

Solution

{{ sec.section }}

{{ it.title }}

{{ it.copy }}

Outcome & Reflection

{{ grp.label }}

Results

  • {{ line }}

Impact

{{ grp.impact }}

If I had more time…

{{ m.title }}

{{ m.copy }}

{{ caseReflection }}

{{ para }}

This project highlights my strengths in:

  • {{ s }}

Employee records — do not distribute

You weren’t supposed to find this.

Since you’re here, you might as well meet the employee keeping this portfolio running.

{{ kiwiNameLabel }}

Senior Portfolio Supervisor

LocationWherever the snacks are
Flight AbilityBest with a parachute
SniffingTop percentile
Lifetime Snacks ConsumedSnack budget exceeded
Years of ExperienceRecords are fuzzy
Current Status{{ kiwiStatusText }}
Contribution to Portfolio{{ kiwiContributionText }}

Kiwi's Cabinet of Mischief

🐾Kiwi Mischief: Complete

Honorary Ground Crew

Your Kiwi Completion — {{ kiwiCompletionLabel }}

{{ ach.displayIcon }}
{{ ach.displayName }}
{{ ach.displayDesc }}
{{ ach.howTo }}

Interested in working together?

Open to AI Engineering and Research Engineering opportunities.
Dhaka, Bangladesh

Find all the hidden AI systems

© 2026 Daud Ibrahim Hassan
🐾

Kiwi Mischief: Complete

Clearance level upgraded.

You have demonstrated an unreasonable level of curiosity.

New title unlocked

Honorary Ground Crew