Senior Engineer - AI Workflows

Xero1 months ago

Location

AU: Sydney (45 Clarence St)

Type

Full Time

Salary

NZD 145,000 – 210,000

Level

Senior

Role

Senior Engineer

Posted

May 6, 2026

Full TimeSenior

The role

Summary

Senior Engineer specializing in AI workflows at Xero's Internal AI Accelerator Squad, leading the design and operationalization of agentic AI solutions across enterprise platforms. This role combines hands-on AI agent development with technical leadership, requiring proficiency in LLMs, cloud infrastructure, and enterprise integration to drive Xero's transformation into an AI-native organization.

What you'll do

Design and Deploy Agentic AI Workflows: Lead the architecture, design, and iterative development of sophisticated AI agents and workflow orchestrations utilizing advanced language models such as Claude and Gemini, with proficiency in Model Context Protocol (MCP) and related frameworks. Translate complex business requirements into elegant, scalable automation solutions that eliminate manual toil and measurably improve operational efficiency across enterprise teams.

Enterprise Platform Integration: Engineer seamless integrations between AI systems and core enterprise platforms including Salesforce, Workday, Slack, and NetSuite. Design robust API connectors, manage authentication flows, and implement reliable data pipelines that enable agentic workflows to operate safely within existing corporate infrastructure while maintaining data integrity and security compliance.

Establish Automation Patterns and Templates: Develop comprehensive, reusable automation patterns and shared templates that serve as blueprints for future AI implementations across Xero. Document architectural decisions, codify best practices, and create developer-friendly resources that empower teams organization-wide to build AI-driven solutions following established patterns and guardrails.

Build AI Safety and Observability Frameworks: Engineer evaluation and monitoring frameworks designed to measure AI agent performance in production environments, detect anomalies, and ensure safety guardrails remain effective. Implement comprehensive logging, tracing, and alerting systems that provide visibility into agent behavior, enabling proactive issue detection and continuous improvement of AI-native workflows.

Technical Leadership and Evangelism: Act as forward-deployed technical partner to internal business teams, conducting workshops and collaborative pairing sessions to elevate AI fluency across Xero. Translate complex technical concepts for non-technical stakeholders, partner with product owners and subject matter experts to identify automation opportunities, and champion best practices in responsible AI implementation.

Drive Rapid Experimentation and Innovation: Contribute to high-velocity squad operations through rapid prototyping, iterative testing, and continuous learning cycles. Collaborate closely with cross-functional teams on complex, messy real-world workflows, refining solutions through direct feedback and demonstrating the tangible business value of intelligent automation to accelerate organizational AI adoption.

Systems Architecture and Security Design: Apply systems-thinking methodology to architect AI agents with security, auditability, and controlled blast radius as core design principles. Design resilient automation patterns with proper error handling, rollback capabilities, and isolation mechanisms that prevent cascading failures while maintaining transparency in decision-making processes for compliance and trust.

AI Centre of Excellence Enablement: Work collaboratively to establish foundations for a future AI Centre of Excellence by documenting lessons learned, creating internal tooling standards, and developing training materials. Define governance frameworks, evaluation methodologies, and operational playbooks that enable broader teams to adopt agentic AI patterns with reduced risk and accelerated time-to-value.

What we look for

Technical

Production Application Development and OperationsDemonstrated expertise in building, deploying, and operating applications in production environments at scale, with deep understanding of reliability, performance optimization, and operational incident response. Experience managing applications handling critical business processes with attention to uptime, monitoring, and graceful degradation.

Large Language Model (LLM) and AI Agent DevelopmentHands-on experience designing and implementing AI-driven solutions including autonomous agents, copilots, retrieval-augmented generation (RAG) systems, and agentic workflows. Proven track record working with production LLM platforms such as Claude (Anthropic), Gemini (Google), or equivalent, including fine-tuning, prompt engineering, and agent orchestration.

Python or TypeScript ProgrammingStrong proficiency in Python or TypeScript with ability to write clean, maintainable production code. Comfortable working with language-specific SDKs, async patterns, dependency management, and testing frameworks. Experience building robust backend services and automation scripts that integrate with external APIs and enterprise systems.

Cloud Infrastructure and API DevelopmentSolid understanding of cloud platforms (AWS, GCP, or Azure) and experience designing RESTful and event-driven APIs. Knowledge of cloud security, authentication mechanisms, webhook handling, and scaling patterns. Experience with infrastructure-as-code tools and containerization (Docker, Kubernetes) for production deployments.

Enterprise Integration and API EcosystemExperience integrating with complex enterprise platforms such as Salesforce, Workday, SAP, or NetSuite. Understanding of enterprise authentication protocols (OAuth, SAML), data transformation, and managing integrations across multiple disparate systems. Familiarity with event-driven architecture and webhook-based system interactions.

Model Context Protocol (MCP) and LLM ToolingFamiliarity with emerging standards and protocols for AI agent interaction, including Model Context Protocol and related orchestration frameworks. Experience building and deploying tool-use capabilities for agents, implementing function calling patterns, and designing extensible agent architectures that support dynamic tool integration.

AI Safety, Evaluation, and MonitoringUnderstanding of AI safety principles, bias detection, and guardrail implementation in production systems. Experience designing evaluation metrics for AI systems, implementing monitoring dashboards for agentic behavior, and creating frameworks to measure agent performance and reliability. Knowledge of responsible AI practices and compliance considerations.

Systems Design and Distributed Systems ThinkingStrong foundation in systems architecture with ability to design fault-tolerant, scalable solutions. Understanding of failure modes, cascading failures, security isolation, and the ability to design agents with controlled blast radius. Experience with async processing, messaging queues, and eventually consistent systems.

Software Engineering Best PracticesCommitment to code quality, including proficiency with version control (Git), testing strategies (unit, integration, end-to-end), continuous integration/deployment pipelines, and code review processes. Experience with observability practices including structured logging, distributed tracing, and metrics collection.

Workflow Orchestration and Automation PatternsExperience designing and implementing complex workflow orchestration using tools such as Apache Airflow, Temporal, or Prefect. Understanding of state management, error recovery, retry logic, and human-in-the-loop approval patterns relevant to enterprise automation scenarios.

Education

Bachelor's Degree in Computer Science or Related FieldFormal education in computer science, software engineering, mathematics, physics, or equivalent discipline demonstrating foundational knowledge of computational thinking and algorithmic problem-solving.

Equivalent Professional ExperienceExtensive professional software engineering experience (typically 7+ years) may substitute for formal education, demonstrating mastery of core computer science concepts through practical application in production environments.

Experience

7+ Years of Software EngineeringSubstantial experience building production applications at scale, with demonstrated expertise in backend development, distributed systems, or platform engineering. Track record of shipping features from conception through operational support and iteration based on production feedback.

3+ Years with AI/LLM TechnologiesHands-on experience actively working with large language models, AI agents, or machine learning systems in professional settings within the last 3 years. Demonstrated ability to navigate rapidly evolving LLM ecosystems and adopt new tools and techniques effectively.

Experience Partnering with Non-Technical StakeholdersProven ability to translate between technical and business languages, extracting actionable requirements from stakeholder pain points. Track record of collaborating with product managers, subject matter experts, and business teams to define solutions that address real operational challenges while remaining technically sound.

Technical Leadership and MentorshipExperience elevating team capabilities through technical coaching, pair programming, knowledge sharing, or formal mentorship. Demonstrated ability to communicate complex technical concepts clearly to diverse audiences and create learning opportunities that accelerate team growth in emerging technologies.

Skills

Required skills

AI Agent Architecture and DesignAbility to architect autonomous agents with proper orchestration, tool integration, and decision-making frameworks. Understanding of agent patterns, including planning-based agents, reactive agents, and hierarchical control structures suitable for enterprise automation scenarios.

LLM Integration and Prompt EngineeringProficiency in integrating language models into production systems, including prompt design, context management, and handling model limitations. Experience optimizing prompts for reliability and cost-effectiveness while managing token usage and inference latency.

Python DevelopmentAdvanced Python programming skills including async patterns (asyncio, aiohttp), type hints, testing frameworks (pytest), and packaging. Comfort with Python-based AI libraries such as LangChain, AutoGen, and LLM SDKs.

TypeScript and Node.js DevelopmentStrong TypeScript proficiency for backend services and tooling. Experience with Node.js runtime, Express or similar frameworks, and type-safe API development. Familiarity with async/await patterns and promise-based concurrency models.

RESTful API Design and WebhooksExpertise in designing clean, scalable REST APIs with proper HTTP semantics. Experience implementing webhook receivers, handling asynchronous events, and designing resilient event-driven integrations between systems.

Cloud Platform ProficiencyHands-on experience with AWS, Google Cloud Platform, or Azure including compute services, storage, networking, and managed services. Ability to design cloud architectures that are secure, cost-effective, and operationally sound.

Security and Authentication ProtocolsDeep understanding of OAuth 2.0, SAML, API key management, and encryption principles. Experience securing production systems, managing secrets, and implementing proper access controls relevant to enterprise environments.

Observability and DebuggingAdvanced debugging skills and proficiency with observability tools including structured logging, distributed tracing (OpenTelemetry), and metrics collection. Ability to diagnose production issues systematically using logs, traces, and performance data.

Workflow Design and State ManagementExperience designing complex stateful workflows with proper error handling, retry logic, and human approval gates. Understanding of state machines and event-driven architecture relevant to robust automation patterns.

Systems CommunicationAbility to communicate technical concepts, architectural decisions, and trade-offs clearly to both technical and non-technical audiences. Skill in documenting complex systems and creating artifacts that enable knowledge transfer and team enablement.

Nice to have

Ray or Distributed Computing FrameworksExperience with Ray, Spark, or similar distributed computing frameworks for parallel processing and large-scale workload management. Knowledge of scaling AI workloads across distributed infrastructure.

Temporal or Advanced Workflow OrchestrationFamiliarity with Temporal.io or similar workflow orchestration platforms for building resilient, long-running processes with proper durability and recovery semantics.

SalesForce, Workday, or NetSuite ExperiencePrior hands-on experience integrating with major enterprise platforms. Understanding of platform-specific APIs, limitations, and integration patterns that accelerate enterprise workflow automation.

Slack or Messaging Platform IntegrationExperience building Slack bots, apps, or integrations. Understanding of event subscriptions, slash commands, and designing conversational interfaces for agents and automation workflows.

Observability Platform ExpertiseAdvanced experience with specific observability platforms such as Datadog, New Relic, Splunk, or Honeycomb. Ability to design comprehensive monitoring strategies for production AI systems.

Generative AI Tools and FrameworksFamiliarity with broader generative AI ecosystems including LangChain, LlamaIndex, AutoGen, or Hugging Face. Experience evaluating and integrating open-source versus proprietary AI components based on use case requirements.

Kubernetes and Container OrchestrationAdvanced Kubernetes experience including designing stateful and stateless workloads, managing resources, and implementing proper deployment strategies. Understanding of container security and orchestration patterns for production reliability.

Finance or Accounting Domain KnowledgeBackground in financial systems, accounting practices, or SaaS operations. Existing familiarity with Xero's domain would provide valuable context for understanding automation opportunities in small business accounting workflows.

Open Source Contribution or Technical Thought LeadershipActive contributions to open source projects, technical writing, conference speaking, or other evidence of technical thought leadership in AI, automation, or distributed systems. Demonstrates commitment to community and continuous learning.

Change Management and Organizational TransformationExperience driving organizational change, scaling emerging technologies across teams, or leading technical adoption initiatives. Understanding of organizational dynamics and stakeholder management in technology transformation contexts.