Senior AI Automation & Integration Engineer

Job Description

Job Description

Description:

JOB OVERVIEW

The Senior AI Automation & Integration Engineer leads the technical execution of the AI Center of Excellence's automation, integration, and enablement capability. Working within the direction established through BS&A's AI engineering standards and governance model, this role defines the implementation patterns, reference components, and reliability standards that other teams build on, and is accountable for those decisions holding up as the AI program scales.

This is an integration, automation, and enablement role, not a model-research, model-training, or GPU-infrastructure role. The focus is internal. AI in our products is owned elsewhere. The work is deciding how approved models connect to BS&A's systems and data, defining the reusable patterns other teams build on, and owning the reliability and cost of those decisions in production.

Where the AI Automation & Integration Engineer configures and integrates within established patterns, this role defines them: how standards become working capabilities, which reference architectures are practical, what belongs in the shared foundation, how evaluation and observability are implemented, and whether a proposed solution conforms to standard. This is a hands-on technical role rather than a people-management role, though it mentors and sets the technical bar for the rest of the capability.

KEY RESPONSIBILITIES

Technical Leadership for Shared AI Capabilities

• Lead the implementation architecture for BS&A's shared AI capabilities, including model APIs and gateways, MCP-based and comparable tool integrations, orchestration workflows, shared frameworks, runtime services, evaluation, monitoring, and cost controls.
• Translate BS&A's AI engineering standards into practical engineering patterns, working capabilities, reference implementations, and technical guardrails that teams can consistently apply.
• Decide, in partnership with the VP of AI Transformation and CTO, what the CoE builds centrally, what departmental engineering builds on shared capabilities, and what is purchased, configured, or intentionally not pursued.
• Establish and maintain reliability, cost, maintainability, and scalability standards as adoption grows across departments.

Solution Engineering & Delivery

• Default to configuring what BS&A already owns or can buy, and build custom only when nothing available does the job.
• Lead the build of enterprise AI solutions where centralized ownership is appropriate, and design the shared components departmental engineering teams build on top of.
• Own technical decisions on build, buy, and configure, including proof-of-concept work and analysis of cost, quality, latency, security, scalability, and maintainability for the highest-stakes solutions.
• Apply and refine the least-expensive-model-capable-of-the-job principle across the portfolio, balancing quality, cost, latency, security, and maintainability rather than optimizing a single solution.

Production Readiness, Reliability & Cost Ownership

• Own the technical readiness assessment for production reviews, complementing the business evidence compiled by the AI Portfolio Analyst and the data, infrastructure, and security assessments owned by IT & Security.
• Own monitoring, evaluation, and cost-tracking instrumentation standards across all production AI solutions, not only those built centrally.
• Lead incident response for CoE-managed components with IT & Security, and drive root-cause fixes that prevent recurrence.
• Define what a complete handoff looks like so solutions transfer cleanly to the team that will own them.
• Own the technical side of the cost-of-value discipline: keeping operating cost within the cost-of-value band defined in the CoE's portfolio standards, and flagging solutions at risk of breaching it.

Standards Execution & Governance Partnership

• Lead the technical execution of BS&A's AI engineering standards, translating architecture, model eligibility, evaluation, and integration requirements into shared components, reference implementations, engineering guidance, and production controls.
• Drive consistent application of those standards across centrally built solutions and departmental engineering teams building on shared capabilities.
• Identify gaps, implementation challenges, and emerging technical needs, and recommend updates to the standards to the VP of AI Transformation, in partnership with the CTO and IT & Security.
• Partner with IT & Security, which owns the data foundation, infrastructure, identity, and security controls AI systems depend on, to keep implementation aligned with company-wide standards.
• Set the standards for defending against prompt injection wherever retrieved content can influence agent behavior, including tool-access limits and least-privilege permissions.
• Define the autonomy ladder for AI solutions, progressing from read-only, to draft and recommend, to action with human approval, and the evidence required to move up it.
• Lead the technical assessment of models and tools considered for the Sanctioned AI Tool List and approved-model register, in partnership with the CoE and IT & Security.
• Represent implementation readiness, technical risk, and areas requiring standards evolution in executive governance reviews and the Quarterly AI Business Review.

Enablement, Mentorship & Knowledge Sharing

• Mentor the AI Automation & Integration Engineer toward shared fluency in BS&A's AI engineering standards and consistent application of them across solutions.
• Set the technical bar for configuration, integration, code, and documentation quality across the capability.
• Create and maintain the deeper technical documentation, training, and reference materials, including MCP, Claude Code, and solution architecture, that raise engineering capability across the company.
• Serve as the escalation point for departmental engineering teams building on shared capabilities.

QUALIFICATIONS

• Seven or more years of professional software, platform, or integration engineering experience, including two or more years building and operating production systems with LLM APIs from Anthropic, OpenAI, or comparable providers.
• Track record of owning a platform, shared service, or developer-enablement capability end to end, covering design, build, reliability, and cost, rather than a single feature.
• Demonstrated ability to build integrations and APIs against enterprise systems such as SharePoint, Confluence, Jira, Salesforce, or comparable platforms, with depth in retrieval, tool calling, or AI orchestration patterns.
• Strong grounding in Microsoft Azure and cloud infrastructure, CI/CD, application deployment, and production monitoring and observability at scale.
• Hands-on depth in at least one low-code automation or agent-orchestration environment such as Copilot Studio, Power Platform, n8n, or Zapier.
• Understanding of data classification, authentication, authorization, access control, secrets management, and secure integration patterns, with experience partnering directly with security and architecture functions.
• Demonstrated ability to set technical direction in new and undefined spaces, build shared tooling and reference patterns where none existed, and defend those decisions to technical and executive audiences alike.
• Demonstrated build-versus-buy judgment at portfolio level, including having chosen an existing managed or purchased capability over building something custom, and having defended that call.
• Experience designing human-in-the-loop workflows, including determining where approval steps belong before an AI solution acts.
• Strong communication skills, with the ability to represent technical tradeoffs to executives and partner closely with architects, engineers, Champions, and business stakeholders.
• Demonstrated judgment about where AI is appropriate, where deterministic software is the better solution, and how to balance experimentation with production reliability.
• Bachelor's degree in Computer Science, Software Engineering, or a related field, or equivalent demonstrable professional experience.

PREFERRED QUALIFICATIONS

• Experience operationalizing a technical architecture, standard, or blueprint: translating it into working capabilities and reference patterns, driving adoption across engineering teams, identifying implementation gaps, and contributing to its continued evolution.
• Deep, hands-on experience with Model Context Protocol or comparable tool-integration protocols and agent frameworks, including having built or extended one.
• Fluency with Claude and the Anthropic ecosystem, including Claude Enterprise or Claude Code, or equivalent depth with another frontier-model provider, including model selection and cost and quality tradeoffs across providers.
• Experience building retrieval-augmented generation, enterprise search, or knowledge-grounded AI applications at production scale.
• Experience with cloud identity and access management, secrets management, infrastructure as code, or containerized application deployment.
• Experience in SaaS, govtech, fintech, the public sector, or another environment involving sensitive customer data.
• Experience in or adjacent to a Center of Excellence, platform-engineering, internal-developer-platform, or developer-enablement function.
• Experience mentoring engineers or informally leading a small technical team without formal management authority.