I am an AI engineer with production experience building agent-based architectures, workflow automation, and privacy-focused governance layers for AI systems. I’m completing a Bachelor of Information Technology at RMIT with a minor in AI and Machine Learning, and I’ve built real-world AI applications including ATB (local-first audit trails), Veritas (execution integrity runtime), and Chaser (evidence-first provenance). I’m ISC2 certified in cybersecurity and focused on secure, auditable AI design. I’m seeking remote, project-based opportunities to design, develop, and deploy AI agents, predictive models, and automation workflows for business clients.
I enjoy turning complex AI and data engineering challenges into reliable, production-ready solutions. My work blends backend services, data pipelines, and governance layers to ensure deterministic, auditable AI behavior while keeping privacy and compliance at the forefront.
Experience Level
Language
Work Experience
Education
Qualifications
Industry Experience
Built Chaser as an evidence-first provenance and governance layer that ingests agent and workflow events, reconstructs deterministic session activity, and produces redacted, integrity-linked artefacts. Implemented a Docker-based stack including backend, frontend, OPA policy engine, Postgres, and OpenTelemetry collector orchestrated via docker compose for local pilots. Added optional shared-secret authentication for governance endpoints configured via environment variables. Created a golden-path demo workflow that exercises the core API, generating cases, sessions, evidence packs, quarantine artefacts, enclave tokens, and controls reports. Defined core outputs such as session replay steps, exposure storylines, evidence packs, enclave workflows, and deterministic controls reports, each backed by evidence identifiers and hashes.
Designed Veritas as a runtime that compiles agent conversations into deterministic execution graphs, persists versioned run history, and records explicit decision resolutions. Implemented policy gating and replay verification so the same inputs and decision resolutions produce the same execution graph, surfacing mismatches as integrity errors. Built a browser-based control plane using React and TypeScript with dashboards, run inspection, audit search, approvals, exports, and operations. Implemented multi-tenant isolation with organisation-scoped runs, decisions, and audit logs, and an API key system for creating, rotating, and revoking keys. Added durable background workers for webhooks and export jobs backed by database leases to support concurrent workers and safe recovery.
Built ATB as a local-first audit trail for privacy-sensitive AI workflows, recording AI events as tamper-evident bundles that can be inspected locally and exported as deterministic evidence. Implemented SHA-256 hash chains over RFC 8785 canonical JSON to detect mutation, reordering, and deletion in recorded traces. Added AES-256-GCM client-side encryption and deterministic export paths for incident review, customer handoff, and internal audit and privacy review workflows. Developed a local viewer and dashboard with timeline, graph, inspector, and privacy reveal audit logging for sensitive data access. Shipped tracing middleware for LangChain in Python and Vercel AI SDK in TypeScript so teams can instrument agents and copilots without relying on hosted observability platforms.
Hire a AI Engineer
We have the best ai engineer experts on Twine. Hire a ai engineer in Mount Waverley today.