Staff AI Platform Engineer

Pushpay is hiring a Staff AI Platform Engineer in Auckland, New Zealand. Level rates it ; you can apply on Pushpay.

Level's read on this job

Level rates this role Builds AI ●●●●: the job is building AI systems.
The posting mentions Claude, LangChain and LangGraph among its tools and skills.
Level classes it as a lead role.
Pushpay has 21 other open roles on Level.

AI in this role

claudelangchainlanggraphbedrockclaude-code

ragai-safety

The Role in 60 Seconds

Most companies are still experimenting with AI wrappers in local environments. At Pushpay, we are building production-grade agentic systems that directly amplify how our entire engineering organization builds, ships, and operates software.

As a Staff AI Platform Engineer, you will operate with significant autonomy to architect, run, and scale our internal agentic platforms and developer tooling (like PR review agents, SDLC copilots, and context engines). You won't just build these systems—you will own their operational discipline, cost governance, evaluation suites, and reliability in production, acting as a force multiplier for every engineer across Pushpay.

Why This Role is Different

True Engineering Leverage: You aren't building internal gimmicks. You are designing systems that fundamentally transform our SDLC and reduce friction for every product team.
Production-Grade Non-Determinism: You treat agents as distributed, operational workloads—implementing token budgets, trace-level observability (OTEL, Langfuse), SLOs/SLIs, and eval-driven regression testing before code hits main.
Influence Without Dictatorship: You won't enforce top-down mandates. You will drive org-wide adoption of tools like Claude Code and custom MCP implementations through technical credibility, pairing with teams, and building platforms engineers want to use.

What You'll Do

Architect & Build Agentic Systems: Design internal supervisor loops, router patterns, and state machines using the Claude Agent SDK, AWS Bedrock, and frameworks like LangGraph.
Run Workloads at Scale: Establish SLOs for agent success rates, latency, and token efficiency. Take point on observability, prompt versioning, and incident response when agents misbehave or hallucinate.
Elevate Developer Experience: Identify SDLC bottlenecks, optimize build/CI performance, refine local dev setups (LocalStack, .NET Aspire), and tune AWS serverless architectures (Lambda cold-starts, SnapStart).
Set the Bar for AI Safety & Quality: Define reusable component models, context retrieval (RAG) architecture, and guardrails to ensure autonomous systems degrade safely.

What We Are Looking For

8+ Years in Software Engineering with significant time spent as a technical lead in Platform, Infrastructure, or DevEx.
Production Agentic Experience: You have actually operated non-deterministic LLM/agentic workloads in production—managing cost governance, tracing, and eval pipelines, not just building prototype wrapper apps.
Backend & Cloud Mastery: Deep proficiency in C# or Python paired with strong AWS cloud-native expertise (Lambda, API Gateway, Bedrock, IAM/KMS).
Developer Empathy & Leadership: A track record of driving tool adoption and technical standards across multiple teams through pairing, mentorship, and clear communication rather than authority.

Tech Stack You'll Touch

Claude Agent SDK • AWS Bedrock • LangGraph / LangChain • OTEL • Langfuse • New Relic • C# / .NET • Python • AWS Lambda • .NET Aspire • LocalStack

Ready to build the platform that powers the future of our engineering organization?

Apply now to join Pushpay's Enablement team as our Staff AI Platform Engineer!
You MUST be eligible to work in NZ to be considered for this role.

How we rate this

Staff AI Platform Engineer at Pushpay rates 85 out of 100 for how much of the daily work is AI. That makes it Builds AI (AI Level 4 of 4). The level is about AI in the job, not seniority.

Classification

Builds AI. The job is building AI systems.

●●●● Builds AI80 to 100
●●●○ Works on AI60 to 79
●●○○ Uses AI40 to 59
●○○○ Little AI0 to 39

Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.

Key facts

Staff AI Platform Engineer is an open job at Pushpay.
Level rates this role AI Level 4 of 4: Builds AI.
The role is based in Auckland.
The job was posted on August 25, 2026.
Seniority: lead.
Applications are handled by Pushpay. Apply on Pushpay

Prepare for this job

Built from this posting and from similar jobs on Level.

Skills and AI tools this role asks for

RAGAI SafetyClaudeLangChainLangGraphBedrockClaude Code

Questions you could be asked

How would you design a retrieval step so the model answers from real data instead of guessing?
How do you think about the risk of an AI system in this kind of role failing silently?
What are the limits of Claude that you've run into, and how did you work around them?
What's a project where you used LangChain hands-on?
Walk me through how you've used LangGraph in your day-to-day work.

Adapt your resume

List these exact terms on your resume: RAG, AI Safety, Claude, LangChain, and LangGraph. An applicant tracking system matches the wording, not the idea.
Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
Lead with what you built, trained or shipped. This role is judged on the AI system itself, not the tools around it.

Want an expert to read your CV for this job?

Free. Send your CV and the role you want next. You get your review by email within 24 hours.

Get a free CV review Get your CV rewritten Check your resume with the ATS resume checker

Get new software engineering jobs (Builds AI ●●●●) by email

One email a week with the new software engineering jobs (Builds AI ●●●●), each rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.

Free. One email a week. Unsubscribe in one click.