Shubham Gupta

Perth, Australia

Senior AI Engineer — Agentic Systems & Enterprise AI Platforms

I build the shared foundations that let engineering teams move AI from prototype to production — governed platforms, grounded assistants, secure model serving, evaluation and developer enablement.

01 PLAN
02 TOOL
03 OBSERVE
04 EVAL
05 SHIP

Download resume Selected work For hiring teams Get in touch

7+ years
Energy / mining / SaaS
Built the Dev Harness
500GB+ enterprise RAG pipeline
Secure model serving across 100+ AWS accounts

LinkedIn GitHub Topmate

Shubham Gupta, Senior AI Engineer based in Perth, Australia

/ About

Senior AI Engineer with 7+ years designing and scaling distributed systems across energy, mining and SaaS environments. Based in Perth and working inside a large Australian enterprise, I build the platform layer beneath AI applications: the Dev Harness for enterprise AI delivery, a 500GB+ enterprise RAG and agent platform, and secure model serving across an estate of 100+ AWS accounts.

I specialise in production-grade agentic AI platforms, LLMOps, MCP/tooling and secure cloud-native architectures — with an engineering focus on evaluation, governance, observability and long-term maintainability rather than demos.

More about how I work

/ Selected work

Internal platform · Paved path

Dev Harness for Enterprise AI Delivery

I built the Dev Harness: an internal paved path for enterprise AI delivery. It packages reusable application templates, deployment automation, MCP and tool-integration patterns, security guardrails, evaluation workflows, observability and CI/CD so an AI application starts from a supportable baseline instead of an empty repository.

Artifact: Reusable AI application templates and reference implementations
Artifact: Deployment automation and CI/CD pipelines for AI services
Artifact: MCP and tool-integration patterns with security guardrails

Read the Dev Harness for Enterprise AI Delivery case study

Retrieval architecture · ReAct agents

Enterprise RAG & Agent Platform

Architected and delivered a scalable enterprise RAG and agent platform: a 500GB+ embedding and ingestion pipeline feeding hybrid search with reranking and vector retrieval, behind a ReAct agent architecture. Retrieval quality was treated as the product — measured chatbot accuracy improved to 95% and response latency was reduced.

Measured: Measured chatbot accuracy improved to 95%
Measured: Response latency reduced
Artifact: 500GB+ enterprise embedding and ingestion pipeline

Read the Enterprise RAG & Agent Platform case study

ML platform · 100+ AWS accounts

Secure Multi-account Model Serving

Designed and implemented a secure ML and model-serving platform spanning 100+ AWS accounts. Open-source HuggingFace models are served through Amazon SageMaker with GPU-backed inference, automated model packaging pipelines and centralised governance controls — so teams keep their own accounts while security and lifecycle standards stay central.

Artifact: Secure ML and model-serving platform spanning 100+ AWS accounts
Artifact: Automated model packaging pipelines for open-source HuggingFace models
Artifact: GPU-backed inference on Amazon SageMaker

Read the Secure Multi-account Model Serving case study

Grounded assistant · Procurement

Enterprise Procurement Knowledge Assistant

Designed and productionised a grounded enterprise Procurement assistant on Azure AI Foundry, using LangGraph for orchestration, ChatKit for the interface, PGVector for retrieval and integrations with MCP servers. Answers stay grounded in trusted enterprise documents, and the architecture was standardised into a reusable reference implementation.

Measured: Reduced inbound procurement support queries by 60%
Artifact: Production Procurement assistant on Azure AI Foundry, LangGraph, ChatKit, PGVector and MCP server integrations
Artifact: Reusable reference implementation standardised from the assistant architecture

Read the Enterprise Procurement Knowledge Assistant case study

Operating model · Platform standards

Enterprise AI Governance & Platform Strategy

Designed the operating model that lets generative AI scale beyond pilots: identity lifecycle and SCIM provisioning, RBAC, a ServiceNow approval workflow, usage controls, licensing and cost governance, plus the ADRs and platform standards that guide technology selection across engineering teams.

Artifact: SCIM provisioning and RBAC model tying AI access to the enterprise identity lifecycle
Artifact: ServiceNow approval workflow for AI capability access
Artifact: Usage controls and licensing / cost governance

Read the Enterprise AI Governance & Platform Strategy case study

All case studies and insights

/ What I do

For hiring teams

Full-time Senior–Staff AI roles

Open to full-time Senior–Staff AI and agent platform roles, remote-friendly from Perth. The recruiter page sets out role fit, how I work and the delivery evidence behind it.

Hire a senior AI engineer Download resume

For teams buying delivery

Contract & fixed-scope consulting

Embedded contract capacity or outcome-scoped projects: platform architecture, agentic reference implementations, evaluation frameworks and AI governance design.

AI engineering services overview

/ Stack

Agentic systems & retrieval

ReAct agent architectures, hybrid search with reranking and vector retrieval on PGVector, LangGraph orchestration and MCP server integrations — grounded assistants built on Azure AI Foundry, with accuracy treated as a measured property rather than an impression.

AI platform & model serving

Internal paved paths for AI delivery: templates, deployment automation, guardrails, evaluation and observability. Open-source HuggingFace models served on Amazon SageMaker with GPU-backed inference and automated packaging across a multi-account AWS estate.

Data & pipelines

Large-scale ingestion and embedding pipelines — including a 500GB+ enterprise corpus — alongside batch and streaming data engineering, warehouse design and data quality instrumentation.

Cloud, security & delivery

AWS and Azure (certified), Terraform and IaC, Kubernetes, CI/CD, observability, SCIM provisioning and RBAC. Python and TypeScript day to day, SQL throughout.

/ Contact

Let's talk about the work.

Open to full-time Senior–Staff AI / agent platform roles (remote-friendly), as well as contract and consulting engagements. Response within two business days.