Staff AI Architect

Job Description

As Staff AI Architect, you own the technical architecture for Domino's enterprise AI platform – spanning classical AI, generative AI, and agentic AI. This is the senior individual-contributor technical authority on AI: you set the direction for how AI capabilities are built, served, orchestrated, and governed, and you drive outcomes through design authority and influence rather than direct reports. You own the reference architecture and the paved road teams build on, and the build-depth judgment for every incoming ask – production now, minimum viable, scaffolded as a contract for later, or deliberately deferred rather than quietly dropped.

This is a deeply hands-on role for an architect who has delivered AI platforms and solutions at enterprise scale – someone who knows why a technique works and when it survives contact with enterprise data, latency budgets, unit economics, and governance, and who still builds prototypes and reference implementations. Our environment is Azure-primary with Databricks.

Responsibilities

Architecture Ownership and Direction

• Own the enterprise AI reference architecture end to end, establishing scalable standards, principles, and design patterns across business groups.
• Own the roadmap for agentic systems platforms, translating business objectives into sequenced technical strategy, milestones, and a build-depth decision for every use case with explicit, traceable reasoning.
• Design and maintain the paved road for AI development – golden patterns for building, serving, evaluating, and integrating models and agents, with an API-first integration default, MCP by exception against explicit criteria, and guardrails inherited rather than bolted on per team – so teams ship without re-solving solved problems.
• Guide optimization of AI compute and token usage as adoption scales, and lead build-versus-buy, model, and framework decisions with evidence – benchmarks, cost per answer, real-load latency.

Semantic Search, Retrieval and RAG Architecture

• Chunking, embedding and indexing: design chunking strategy per content type and tune size, overlap, and boundaries against measured retrieval quality; select and evaluate embedding models; own re-embedding and versioning.
• Query construction and hybrid retrieval: implement query rewriting, decomposition, and expansion; combine dense and sparse retrieval with fusion and re-ranking; manage the recall-versus-precision and latency trade-off explicitly.
• Retrieval and response evaluation: instrument recall, precision and faithfulness against curated golden datasets; ground answers in the certified semantic layer and knowledge graphs where they outperform vector retrieval; design for graceful abstention over confident wrong answers.

Generative AI Portfolio

• Define prompt and instruction management standards – versioning, templating, context budgeting, and regression testing on prompt or model changes.
• Own the AI gateway and multi-model routing, matching each request to the right model on complexity, cost, latency, and quality, and own the benchmarking discipline for how models are compared, selected, and re-tested as the landscape shifts.
• Establish the evaluation harness as a launch gate – offline/online evaluation, LLM-as-judge with human calibration, A/B and shadow testing, and an explicit quality threshold we won't launch below.
• Hold a clear, evidence-based position on when prompt engineering suffices versus when fine-tuning or customization is warranted, and define caching strategy as a deliberate cost and latency lever.

Agentic AI Portfolio

• Architect the orchestration layer that chains agents, tools, retrieval, and human review – orchestration as the enforced contract, domain agents scoped by journey and business context, and a reusable skills and tool layer where reusability actually lives.
• Design memory and context management with an explicit position on what persists, for how long, and under what access rules; define enterprise standards for tool/function calling and MCP server contracts.
• Establish agent guardrails – authorization scope, permission models, approval and escalation paths, sandboxing, fallback behavior, and safe failure – plus step-level tracing, regression testing, audit, and incident response.
• Define the agent registry, tool catalog, memory and state services, and lifecycle from prototype to monitored production asset, and apply agentic patterns – spec-driven development, AI-assisted code and test generation – to our own engineering practice.

Governance, Trust and Security

• Define responsible AI standards – bias/fairness testing, transparency, explainability, and human oversight on high-risk outputs – aligned with enterprise data governance policy rather than parallel to it.
• Establish AI security patterns for prompt injection, data exfiltration, jailbreaks, and model/supply-chain risk; partner with the Data Governance team on classification, stewardship, certified sources, and access controls – Microsoft Purview, Entra ID, Unity Catalog, row-level security, PII handling, and retention.
• Classify use cases by risk, drive attestation with Security, Legal, Privacy, and Risk, and lead third-party model/vendor technical review, translating findings into architecture constraints.

Observability, Economics and Platform Engineering

• Instrument tracing, telemetry, and drift signals from day one so agent behavior is observable before it's questioned; build cost attribution and drive cost per successful answer as a first-class metric.
• Contribute to the instrumentation that ties AI investment to measurable outcomes –partnering with platform and finance teams so unit economics are a first-class design constraint.
• Define the Azure-native platform stack and lifecycle with MLOps and Engineering – Azure AI Foundry, Azure ML, AKS, model/agent registry, CI/CD, landing-zone and environment strategy, Entra ID and network patterns, capacity, and LLMOps/AgentOps for versioning, promotion, and rollback.
• Partner with Engineering and Architecture teams on data readiness, certified metrics, lineage, and data contracts, and with Engineering on turning reference patterns into shipped services – defining the sanctioned builder environment so teams move fast without bypassing controls.

Technical Leadership

• Raise the bar across Engineering and solution architecture through design reviews, system-level reasoning, and mentorship – driving rigor without direct reporting relationships.
• Translate architecture trade-offs into clear, decision-oriented narratives for senior technology leaders and peer architects, and lead cross-team decisions with partners such as Microsoft, Databricks, strategic AI vendors, and systems integrators.
• Write architecture decision records, reference patterns, and reusable accelerators, and develop proof-of-concept reference implementations that help teams move AI solutions from concept through production without rebuilding the controls.

Qualifications

• Deep enterprise architecture and systems-design expertise. Proven ability to design end-to-end AI platforms spanning applications, models, data, APIs, integration, identity, infrastructure, and operations. Strong grounding in distributed systems, event-driven and service-oriented patterns, resilience, high availability, fault tolerance, and disciplined architectural decision-making.
• Strong foundations in AI, machine learning, and generative AI. Deep understanding of classical ML, deep learning, NLP, foundation models, transformers, embeddings, semantic retrieval, RAG, fine-tuning, multimodal AI, and agentic or multi-agent architectures, including when to use each approach, how to weigh the trade-offs, and where each one can fail.
• Data, retrieval, and knowledge architecture expertise. Ability to design structured and unstructured data ingestion, transformation pipelines, chunking and indexing strategies, vector and hybrid retrieval, knowledge graphs, metadata models, lineage, provenance, data quality, and access controls, including grounding conversational experiences in structured data (text-to-SQL, multi-turn dialogue).
• Model evaluation and production lifecycle engineering. Experience establishing evaluation frameworks and benchmarks (recall@k, NDCG, groundedness, LLM-as-judge), automated testing, release controls, model and prompt versioning, observability, quality monitoring, incident response, rollback, and ongoing improvement using MLOps and LLMOps principles.
• Security, privacy, responsible AI, and governance. Ability to build identity, authorization, privacy, model security, human oversight, regulatory controls, and auditability into the architecture from the start. Must understand AI-specific threats such as prompt injection, sensitive-data leakage, unsafe agent actions, and model or software supply-chain risk.
• Scalability, reliability, performance, and AI economics. Ability to make quantitative architecture decisions on latency, throughput, concurrency, availability, capacity, inference architecture, compute utilization, quality-versus-performance trade-offs, consumption forecasting, and cost optimization, including AI FinOps at scale.
• Business and value-oriented solution architecture. Ability to translate business strategy into qualified AI use cases, measurable outcomes, target-state architectures, investment priorities, and delivery roadmaps. Must separate value-producing opportunities from technology demos and tie solutions to operational or financial KPIs.
• End-to-end delivery with hands-on technical credibility. Demonstrated ability to move from discovery and architecture through experimentation, production deployment, and operational improvement. Able to build or review prototypes (Python, SQL, Spark), validate assumptions, review implementation designs, diagnose cross-layer failures, and defend technical trade-offs, with production depth in DevSecOps, Infrastructure as Code, Kubernetes, and model serving.
• Technical leadership and stakeholder influence. Experience defining reusable patterns and standards, leading architecture reviews, mentoring engineers and architects, and aligning product, data science, engineering, infrastructure, security, and business teams. Creates clarity in ambiguity, leads with integrity and humility, and communicates well with executives and practitioners alike.
• Substantial enterprise AI delivery experience. A strong record of leading complex AI or ML solutions in production at enterprise scale, typically 10+ years across software, data, or ML engineering with significant architecture leadership.

Preferred Qualifications

• Hands-on experience with Microsoft environment: Azure (AI Foundry and Agent Service, Azure OpenAI, Azure ML, AI Search, API Management, Functions), Databricks and Copilot Studio; agent frameworks such as LangGraph or Semantic Kernel and MCP.
• Experience in retail, restaurant, e-commerce, or supply chain with high-volume, real-time workloads and streaming (Kafka, Event Hubs) and model risk management.
• Production multi-agent systems and agent runtimes, policy-aware agent gateways with authenticated tool routing and server registries, and GPU-accelerated serving stacks.
• Contributions to open-source AI projects, published work, or recognized community involvement.

Additional Information

Benefits:

• Paid Holidays and Vacation   
• Medical, Dental & Vision benefits that start on the first day of employment
• No-cost mental health support for employee and dependents
• Childcare tuition discounts
• No-cost fitness, nutrition, and wellness programs 
• Fertility benefits
• Adoption assistance
• 401k matching contributions   
• 15% off the purchase price of stock   
• Company bonus   

All your information will be kept confidential according to EEO guidelines.