About Techxavant:
TechXavant is built by a founding team with more than 100 years of combined experience and a proven track record of building and growing successful technology ventures. Together with our strategic partners, we are addressing opportunities across leading banking, financial services, insurance, superannuation, telecommunications, energy and utilities organisations. Our focus is on creating transformative service offerings by combining deep engineering expertise across AI, cloud, blockchain and cybersecurity with the capabilities of some of the world’s leading technology organisations.
About the Role
We are seeking an innovative AI Platform Engineer to lead the evolution of our developer ecosystem into an AI-native engineering factory. In this role, you will bridge the gap between cloud infrastructure and cutting-edge developer toolchains. You will design, build, and maintain a highly secure, governed, and automated developer platform hosted on Google Cloud Platform.
Candidates with equivalent AI integration and tooling expertise in AWS or Azure, combined with prior exposure to GCP, will also be considered.
Your core objective will be to move our software delivery lifecycle beyond basic AI autocomplete toward agentic coding. You will build the foundation that connects external agentic IDEs and tools (such as GitHub Copilot and Cursor IDE) with GCP-native features (Vertex AI Codey/Gemini, Cloud Run, and Vertex AI Model Garden) to create seamless, automated, and context-aware development workflows.
Key Responsibilities
1. Agentic Tooling & IDE Integration
- Next-gen Developer Environments: Design and implement next-generation AI-assisted developer environments integrating tools like Claude Code, Cursor IDE and GitHub Copilot safely into enterprise workflows.
- Context Engineering & Indexing: Build automated pipelines that supply agentic tools with rich context—indexing enterprise infrastructure repositories, Terraform modules, design docs, and service catalogs.
- Bespoke Extension Development: Create custom plugins or Model Context Protocol (MCP) servers to expose internal GCP metrics, data patterns, and deployment pipelines directly to AI coding agents.
- Observability Tooling: Experience setting up LLM monitoring ecosystems (evaluations, semantic tracing, token cost Tracking, and drift monitoring).
2. GCP AI Platform & Infrastructure Engineering
- Native AI Feature Exploitation: Leverage Google Vertex AI (including Gemini models, Code Models, and Agent Development Kits) to provide native AI features alongside third-party IDE tools.
- Execution Sandboxes: Build and manage isolated execution sandboxes (using Google Kubernetes Engine (GKE) or Cloud Run) where autonomous agents can safely plan, write, run tests, and iterate on code.
- Infrastructure as Code (IaC): Treat the entire AI toolchain as infrastructure using Terraform, ensuring environment repeatability, prompt versioning, and unified configurations.
3. Guardrails, Quality Gates & Governance
- Automated Code Quality & Review Gates: Establish automated guardrails that intercept agent-generated code to run structural validation, security scanning via integration of security scan tools compliance audits.
- Cost & Token Optimization: Implement enterprise-wide observability, logging, and rate-limiting dashboards to monitor token consumption, latency, and costs across different coding assistant models.
- IP Safeguarding & Privacy: Configure GitHub Copilot, Cursor, and Gemini to ensure proprietary code never leaves our strict GCP boundaries or trains public foundational models.
4. Developer Enablement & Mentorship
- Document best practices for context engineering, multi-agent orchestration patterns, and software specification writing.
- Educate and mentor engineering teams on transitioning from manual "vibe-coding" to structured, agentic development models.
Required Skills & Experience
- Cloud Expertise: 5+ years of experience building and scaling production platforms on GCP using managed services such as Cloud Run, GKE, BigQuery, and Secret Manager.
- AI/ML Platform Knowledge: Direct experience working with Vertex AI, foundational LLM APIs or RAG pipelines.
- Advanced Developer Tooling: Deep technical familiarity with the internal configuration, context-indexing mechanisms, and enterprise administration of GitHub Copilot, Cursor IDE, or terminal-native agents (e.g., Claude Code).
- Automation & Coding: Strong scripting and programming experience in Python, Go, or TypeScript/Node.js for building internal developer tools, CLI utilities, and API integrations.
- DevOps/Platform Engineering Mindset: High proficiency with Terraform, GitHub Actions, CI/CD pipeline structures, and cloud-native observability (Cloud Logging/Monitoring, Prometheus, or Grafana).
- Systems Architecture: Experience designing secure network boundaries, IAM policies, and VPC structures for internal data exchange.
Location and Work Rights:
We are seeking candidates with unsrestricted full-time work rights in Australia who do not need immediate sponsorship for the next 12 months.
The role is Melbourne based and candidate is expected to work at least 3 days at our Melbourne office or client offices while flexibility is available to work from home.
Preferred/Nice-to-Have Qualifications
- Experience deploying or customising Model Context Protocol (MCP) servers.
- Active personal projects using any open-source agentic frameworks (e.g., LangGraph, AutoGen, CrewAI).
Pay: From $130,000.00 per year
Benefits:
- Employee mentoring program
- Extended annual leave
- Professional development assistance
- Referral program
- Relocation assistance
- Visa sponsorship
Work Location: Hybrid remote in Richmond VIC