Key Responsibilities

1. Azure AI and Automation Architecture

·       Lead architecture and hands-on technical direction for Azure-based AI, agentic automation, and enterprise integration solutions

·       Design practical solutions using Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure Functions, Azure SQL, Blob Storage, Cosmos DB, Application Insights, and related services as applicable

·       Design LLM orchestration, prompting, grounding and RAG, tool and function calling, evaluation, guardrails, confidence handling, and human-in-the-loop controls

·       Evaluate trade-offs among AI-driven extraction, deterministic rules, workflow engines, RPA, and traditional integration patterns

2. ServiceNow AI BPO Integration

·       Own the Azure intelligence, decisioning, and integration layer supporting ServiceNow-based user experiences and business workflows

·       Partner with the ServiceNow Architect to define clean boundaries between ServiceNow orchestration and Azure-hosted AI or integration logic

·       Design secure APIs, interface contracts, data mappings, asynchronous processing, error handling, logging, monitoring, and operational fallback mechanisms

·       Ensure AI outputs can be consumed safely and auditably by ServiceNow workflows, business users, and downstream systems

·       Lead knowledge transfer from external vendors and offshore resources into our client, and convert it into reusable documentation, standards, and runbooks

·       Support and mentor peers over time, and help reduce dependency on external vendors for core technical delivery

3. GitHub, Code Review and SDLC Governance

·       Establish and enforce engineering standards for GitHub, pull requests, branching, code reviews, merge readiness, and work-item traceability

·       Review vendor- and offshore-developed code for maintainability, security, scalability, testing discipline, and architecture alignment

·       Ensure pull requests are appropriately scoped, independently testable, linked to requirements, and supported by meaningful test evidence

·       Define CI/CD and release controls across development, test, UAT, and production environments, including dependency and configuration validation

·       Create reusable reference architectures, coding standards, templates, review checklists, evaluation methods, deployment playbooks, and support runbooks

4. AI Quality, Security and Operational Readiness

·       Define evaluation frameworks and acceptance criteria for accuracy, grounding, explainability, latency, reliability, and business usefulness

·       Design controls for prompt injection resistance, data leakage prevention, content safety, model usage management, and responsible AI operation

·       Implement observability patterns for model calls, tool executions, failures, cost and token usage, response time, and end-to-end transaction tracing

·       Collaborate with infrastructure and security teams on managed identity, secrets management, private networking, access controls, privacy, and compliance requirements

5. Stakeholder and Cross-Cultural Leadership

·       Partner with U.S., Japan, vendor, offshore, and business stakeholders across technical and non-technical audiences

·       Prepare architecture diagrams, decision records, risk assessments, structured progress updates, and executive-level explanations

·       Work effectively in a Japanese corporate environment where alignment, documentation, relationship-building, and measured decision-making are important

·       Maintain accountability for technical quality, delivery outcomes, and transparent communication of risks, assumptions, and dependencies

Required Skills and Experience

·       6+ years of experience in enterprise software engineering, cloud architecture, automation, integration, or AI-enabled systems

·       Strong hands-on experience designing and implementing solutions on Microsoft Azure

·       Practical experience with Azure AI Foundry and Azure OpenAI, including deployment, orchestration, evaluation, and production risk controls

·       Strong knowledge of GenAI solution design, including LLM orchestration, prompt design, grounding and RAG, tool or function calling, evaluation, guardrails, and human-in-the-loop patterns

·       Experience leading technical delivery across requirements, architecture, build, code review, testing, UAT, release, and stabilization

·       Proven experience establishing GitHub-based engineering standards, pull request and code review processes, CI/CD practices, and technical governance

·       Ability to perform hands-on architectural and technical review of application code, infrastructure configuration, APIs, pull requests, test evidence, and deployment readiness

·       Strong API, integration, asynchronous processing, and data-flow design experience across enterprise systems

·       Experience with identity, secrets management, private networking, logging, monitoring, and secure cloud design

·       Experience mentoring engineers or helping build an internal engineering or platform capability

·       Experience working with distributed teams, external vendors, offshore resources, and business stakeholders

·       Excellent written and verbal communication skills in English, including clear technical documentation and executive summaries

·       Must be legally authorized to work in the United States

Technical Competencies

·       Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure Functions, Azure SQL, Blob Storage, Cosmos DB, Application Insights, and Azure identity and networking patterns

·       GenAI and agentic solution patterns: LLMs, prompting, RAG, evaluation, tool and function calling, guardrails, AI observability, hallucination and risk controls, and human review

·       GitHub and Azure DevOps: repository strategy, branching, pull requests, code review, work-item traceability, build and release pipelines, CI/CD, and environment controls

·       Programming and integration using Python, REST APIs, JSON, event-driven or asynchronous patterns, and cloud-native services

·       Architecture governance: reference patterns, architecture decision records, non-functional requirements, threat and risk review, and production readiness

·       Operational engineering: monitoring, logging, tracing, incident troubleshooting, cost and performance optimization, rollback planning, and support runbooks

·       Security and compliance: managed identity, role-based access control, Key Vault and secrets, private endpoints, privacy, auditability, and enterprise change management

Preferred Qualifications

·       Experience integrating Azure AI or custom applications with ServiceNow, enterprise workflow platforms, or BPO solutions

·       Experience with Microsoft Copilot, Copilot Studio, Power Platform, or Microsoft 365 enterprise integration

·       Experience with Snowflake, Sigma, Databricks, SAP, ERP integrations, RPA, or enterprise data platforms

·       Experience transitioning projects from system integrators or consulting partners to internal engineering teams

·       Experience building a small AI engineering practice, automation center of excellence, platform team, or reusable delivery capability

·       Experience with finance, procurement, contract creation, invoice processing, shared services, or other controlled enterprise workflows

·       Experience working with Japanese companies or Japan-U.S. cross-cultural teams; Japanese language ability is a plus but not required

·       Interest in Japanese business culture, consensus-oriented communication, and long-term stakeholder relationships

·       Relevant Microsoft Azure, AI, cloud architecture, security, or enterprise architecture certifications are a plus

What Success Looks Like

·       Azure AI and automation architecture is clear, documented, secure, supportable, and reusable across multiple business use cases

·       ServiceNow and Azure responsibilities are clearly separated with reliable interface contracts and end-to-end observability

·       Vendor-developed code is reviewable, traceable to work items, independently testable, and compliant with agreed engineering standards

·       AI solutions have defined quality measures, guardrails, human fallback, monitoring, and production operating procedures

·       UAT and production releases avoid preventable environment gaps, configuration drift, and dependency surprises

·       Our client engineers increasingly own architecture, implementation, code review, release, and support without relying on external vendors for core technical delivery

·       Reusable reference architectures, templates, standards, evaluation methods, and engineering playbooks are established for future automation projects

·       Trust is built with U.S., Japan, business, vendor, and offshore stakeholders through structured communication and reliable technical leadership