About the Role
You'll be joining the Developer Experience (DevEx) team within our broader Kaluza Technology community. We’re a large team of both data-led and product focused Software and Production Engineers, pushing the boundaries of technology and working at an extraordinary scale. As a collective we strive for engineering greatness and by ensuring best practices across the board of the community.
In this role, you’ll play a pivotal role in architecting and evolving our Internal AI Engineering Platform. You'll be building the infrastructure—from Model Context Protocol (MCP) servers to shared agentic workflows—that empowers our software teams to move faster and more securely. Your work will directly impact how Kaluza eliminates defects, scales productivity, and defines the gold standard for AI-augmented development.
Our tech stack is very fluid, but broadly you can find yourself working with: AWS, Kubernetes, LLMs (Claude, GPT, etc.), MCP servers, LangChain/LangGraph, and modern observability tools.
Responsibilities
- AI Tooling Orchestration: Lead the trials and deployment of next-generation engineering tools, including Claude Code, Kiro, and Opencode, ensuring they integrate seamlessly into the developer inner loop.
- Infrastructure & Connectivity: Design and maintain our MCP (Model Context Protocol) registry, establishing a secure and scalable process for approving and deploying new servers and tools.
- Agentic Workflows: Develop and maintain "Shared Agents" and agents.md standards to standardize coding styles and automate repetitive architectural tasks.
- Spec-Driven Development: Build and evangelize "Build Your Own" AI solutions and low-code automations that support spec-driven development, reducing the gap between requirements and production code.
- Enablement & Governance: Author high-quality onboarding documentation, security guidelines, and "Golden Path" examples that help engineers leverage AI safely and effectively.
- Performance Analytics: Architect and automate the tracking of AI Impact Metrics, specifically focusing on the volume of AI-generated contributions within PRs and their correlation to code quality and velocity.
- Security & Cost Optimization: Partner with security and finance teams to ensure our AI usage reinforces our security safeguards and remains cost-efficient at scale.
Requirements
- Production-Grade AI Implementation: You have experience building and running production systems, but you’re also deeply curious about the "LLM-ops" lifecycle—moving beyond chat interfaces to integrated agentic workflows.
- Systems Thinker: You possess a solid foundational knowledge of distributed systems and understand how to integrate third-party AI APIs (like Claude or OpenAI) without compromising system reliability or latency.
- Infrastructure as Code & Beyond: You have hands-on experience with AWS in production, and you treat AI prompts, MCP configurations, and agent definitions with the same version-control rigor as your infrastructure.
- The DevEx Mindset: You are passionate about developer productivity. You don’t just build tools; you build experiences that make an engineer's day-to-day life easier and more creative.
- Security & Governance First: You understand the risks of AI (data leakage, prompt injection) and can design approval processes and security guardrails that protect the business without slowing down innovation.
- Data-Informed: You enjoy defining and automating metrics—like tracking AI-generated code volume or PR velocity—to prove the value of the tools you deploy.
- Collaboration: You are a strong communicator who can translate complex AI concepts into clear guides, onboarding docs, and shared best practices for the wider engineering community.
- Curiosity: The AI landscape changes weekly. You are motivated to continuously trial new tools and aren't afraid to pivot when a better solution emerges.