Staff AI Platform Engineer

Engg

Auckland

On-site

NZD 180,000 - 240,000

Full time

14 days+

Application generator

Don’t send a generic resume — generate a resume and cover letter tailored to this exact role.

Get past ATS filters

Job summary

Pushpay is seeking a Staff AI Platform Engineer to architect, run, and scale internal agentic platforms and developer tooling. You’ll own operational discipline, cost governance, evaluation suites, and reliability in production, enabling every engineer to move faster.

In this role you’ll design supervisor loops, manage SLOs, and drive observability with OTEL and Langfuse, while improving SDLC tooling and local dev setups. NZ work eligibility is required.

Qualifications

Proven leadership in platform, infra or DevEx with a track record of delivering scalable systems.
Strong hands-on skills in C#/.NET and Python within cloud-native environments.
Experience with cost governance, observability, and production-grade reliability.
Familiarity with agentic AI tooling and developer productivity platforms.

Responsibilities

Architect and build internal agentic systems and supervisor loops using Claude/Bedrock.
Run workloads at scale with defined SLOs, latency targets, and token efficiency.
Own observability, prompt versioning, and incident response for agent behavior.
Improve developer experience by optimizing SDLC tooling and local dev setups.
Set safety and quality guardrails for autonomous systems and context retrieval.

Skills

Platform/Infra leadership

C# / .NET

Python

AWS cloud-native

DevEx tooling

Tools

Claude Agent SDK

AWS Bedrock

LangGraph

LangChain

OTEL

Langfuse

New Relic

LocalStack

Job description

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