Open to AI Engineer roles

Suhail Shah

AI Engineer

I build AI systems that turn complex documents and user intent into reliable outcomes, from retrieval and document intelligence to agents that plan, act, and verify.

Let’s talk AI
Retrieval + Document Intelligence
Agentic Systems + Tool Use
Evaluation + Observability

Experience

Professional AI delivery across document intelligence, grounded retrieval, and agentic software built around evidence and human control.

fourpoketAI Developer ToolsFeb 2026 - Sep 2026

AI Coding Agent

AI Engineer

Created and deployed an AI coding-agent MVP, taking a requested change from an evidence-grounded plan to approved local edits and project verification. Delivered the agent orchestration, repository retrieval, tool controls, and evaluation workflows across the CLI and supporting services.

Agent orchestrationHybrid retrievalContext engineeringTool callingApproval gatesEvals & session receipts
Core stackPython · TypeScript · FastAPI · Tree-sitter · PostgreSQL · pgvector
Outcomes
▸Deployed a coding-agent MVP that turns a requested change into a plan, approved edits, and verification results
▸Kept execution local, required approval, and rejected ambiguous edits so the agent could recover without guessing
▸Grounded answers and plans in code and trusted documents with inspectable source citations
▸Made behavior inspectable through reproducible evaluations and receipts showing evidence, checks, usage, and cost
Etiqa Insurance & TakafulDocument AI · RAG · Enterprise WorkflowsApr 2024 - Nov 2025

Document Intelligence & Grounded Case Assistance

AI Engineer

Worked as the AI engineer within a wider enterprise approval and workflow platform. Focused on document processing, structured extraction, retrieval, and grounded case assistance, then integrated those AI services with the existing application. The wider team owned most of the workflow and approval functionality.

Document ingestion & OCRStructured extractionEmbeddings & retrievalGrounded RAGSource referencesHuman review safeguardsAI service integration
Core stackPython · FastAPI · Pydantic · PostgreSQL · OCR · RAG · Celery · React
Outcomes
▸Delivered OCR and structured extraction for documents attached to approval cases
▸Built grounded case assistance that answered with relevant source evidence
▸Connected AI processing to the existing application through APIs and background jobs
▸Kept extracted values and generated answers reviewable through confidence and validation checks
▸Supported the React and TypeScript integration for AI-facing parts of the product
SunwayEvent Security Staffing & Attendance VerificationSep 2022 - Mar 2024

Event Security Operations Platform

Senior Full Stack Engineer

Built an event security operations platform that unified event setup, shift planning, guard records, attendance verification, live operations monitoring, incident reporting, patrol tracking, audited overrides, and invoice discrepancy review. The platform gave operations and commercial teams a reliable source of truth for staffing coverage, verified hours, no-shows, exceptions, and supporting evidence, while integrating with a separate Android guard app through shared API contracts.

Event staffing operationsQR/GPS attendance verificationLive operations dashboardInvoice reconciliationMobile API contractsOn-prem deployment
Core stackReact · TypeScript · Node.js · Express · PostgreSQL · PostGIS · Socket.IO · Redis
FreelanceInventory, Orders, Purchasing & ReportingMar 2021 - May 2022

Inventory, Orders & Reporting Platform

Full Stack Engineer

Built a single-tenant internal operations platform for a wholesale distribution business that had outgrown spreadsheets. The system replaced separate stock and order workbooks with one database-backed workflow covering products, customers, stock movements, sales orders, purchase orders, warehouse picking, stocktakes, dashboards, reports, audit history, and accountant-ready exports.

Inventory operationsOrder lifecycleStock movement ledgerWarehouse tablet viewsReporting dashboardsFreelance delivery
Core stackReact · TypeScript · Python · FastAPI · PostgreSQL · Docker · SQLAlchemy · Alembic
AccentureSchema-Driven Forms, Shared Libraries & Delivery AccelerationFeb 2019 - Jan 2021

Schema-Driven Form Engine

Software Architect

Architected and built a schema-driven form engine for a large enterprise client whose systems centered on multi-step form journeys. The engine let delivery squads declare journeys as JSON, render them through a shared React library, validate them again on the Node.js backend, version schemas centrally, and release new field capabilities through a private npm package workflow.

Schema-driven formsReact rendererPlugin architectureServer-side validationSchema versioningPrivate npm packages
Core stackReact · TypeScript · Node.js · Express · MySQL · AWS · Docker · Storybook
VistraShare Registration, IPO & Investor E-ServicesAug 2017 - Jul 2018

Share Registration & Investor E-Services

Full Stack Engineer

Worked across an investor e-services platform supporting shareholder submissions, IPO-related flows, internal back-office operations, and corporate website maintenance. Built and extended form modules, maintained PHP features, wrote MySQL queries and reports, and handled front-end work with HTML, CSS, JavaScript, and jQuery.

Investor e-services portalIPO & balloting systemsInternal admin toolsForm modulesMySQL reportingPHP maintenance
Core stackPHP · MySQL · JavaScript · jQuery · HTML · CSS

Open Source

Personal AI systems work, built in public with readable source.

Personal projectAI toolingGitHub ↗2026

learning-system

Public source, actively developed

A local learning platform where an LLM acts as the teacher and a typed Python backend owns memory, orchestration, and context engineering. The public source spans the applied AI stack: provider abstraction over two model transports, pgvector retrieval, a versioned eval framework with regression reporting, OpenTelemetry tracing, and an approval-gated agent layer.

Agent orchestrationEval frameworkLLM observabilitypgvector retrievalTool callingHuman-in-the-loop
Core stackPython · FastAPI · Pydantic · PostgreSQL · pgvector · OpenTelemetry · pytest
Outcomes
▸Public commit history with signed commits and pre-commit gates for lint, strict typing, and commit format
▸Versioned eval sets run against either transport with deterministic and LLM-as-judge scoring
▸A regression report diffs each eval run against the last, per set and per item
▸Every LLM round trip is recorded with latency and cost fields and linked to traces and error logs
▸Agent mutations apply atomically behind a human approval gate, and failures survive rollback
▸Smoke scripts verify transport contracts against live providers, separate from the unit suite

About

Hey, I'm Suhail Shah. I'm an AI Engineer based in Kuala Lumpur, Malaysia. I build systems that retrieve relevant evidence, understand documents, take controlled actions, and make their results easy to verify.

At Etiqa, I focused on the AI layer inside an enterprise approval and workflow platform, building document intelligence and grounded case assistance. At fourpoket, I delivered a coding-agent MVP, with grounded plans, approved local execution, and verification receipts. My personal learning-system project explores agent orchestration, evaluation, retrieval, and LLM observability in public.

Useful AI takes more than a model call. It needs the right context, clear permissions, reliable tools, careful evaluation, and human judgment. I bring 7+ years of software engineering experience to that work, with my career focused on AI engineering.

Suhail is often associated with Canopus, one of the brightest stars in the night sky. Across history, Canopus has been used as a navigational star, a fixed point for finding direction across long distances.

I like that connection because it matches the kind of engineering I care about: making complex systems easier to navigate, turning ambiguity into direction, and building tools people can trust when the path is not obvious yet.

Retrieval & Grounding
Embeddings, retrieval, context construction, and source references that connect answers to evidence.
Document Intelligence & Retrieval
OCR and structured extraction that turn complex documents into reviewable information.
Agentic Systems
Planning, tool use, context engineering, approval gates, and verifiable execution.
Evaluation & Governance
AI evaluation, observability, guardrails, and feedback loops that improve reliability over time.
What I Bring
Applied AI SystemsLLM Agents & Tool UseRAG & Hybrid RetrievalEmbeddings & RerankingDocument IntelligenceAI Evals & ObservabilityAI Safety & GuardrailsPython AI ServicesContext EngineeringAsync AI PipelinesMulti-Provider AIAI Product Delivery

Get in Touch

Building agents, retrieval, document intelligence, or production AI systems? Let's talk.

Open to AI Engineer roles · Kuala Lumpur, Malaysia · Remote

suhailshah.dev@gmail.comGitHubLinkedInfourpoket.comnpm: fourpoket