Senior Data Architect

• Own end-to-end architecture for enterprise GenAI solutions — retrieval, orchestration, integration, and evaluation — ensuring they are scalable, secure, and aligned to business outcomes.
• Design production retrieval-augmented generation (RAG) architectures over enterprise data, including document ingestion and chunking, indexing strategy, hybrid lexical and semantic retrieval, re-ranking, and relevance tuning.
• Architect multi-phase agent and tool-calling workflows with deterministic guardrails — scoped tool access, structured output schemas, validation, bounded retries, explicit completion contracts, and fallback handling — so that non-deterministic models meet production reliability standards.
• Design the data ingestion and synchronization foundations that support AI grounding — streaming and change data capture from enterprise sources, canonical data models, and incremental sync that keeps indexes and downstream systems current.
• Enforce data governance and strict multi-tenant isolation boundaries across brands, regions, and partners, applying access control, PII protection, and Responsible AI principles by default.
• Establish evaluation and observability standards for AI workloads — curated test sets, automated quality scoring including model-based judging, regression suites in CI/CD, and end-to-end tracing of model behavior in production.
• Own the operational economics of AI systems: latency and throughput targets, inference and token cost management, caching strategies, and routing work to the appropriate model for the task.
• Act as the principal technical authority for AI architecture — lead design reviews, resolve complex performance and integration issues, mentor engineers, and champion Agile, DevOps, and CI/CD practices.

• A hands-on architect who can independently design end-to-end solutions while remaining active in development, code review, and production problem-solving.
• Treats AI systems as distributed data systems — designs for failure, latency, duplication, and drift rather than assuming the happy path.
• Collaborative and self-motivated, able to work across global teams, influence stakeholders without formal authority, and translate business needs into scalable technical solutions.

We produce globally recognized brands, and we grow the best business leaders in the industry.

With a portfolio of trusted brands as diverse as ours, it is paramount our leaders are able to lead with courage the vast array of brands, categories and functions.

We serve consumers around the world with one of the strongest portfolios of trusted, quality, leadership brands, including Always®, Ariel®, Gillette®, Head & Shoulders®, Herbal Essences®, Oral-B®, Pampers®, Pantene®, Tampax® and more.

Our community includes operations in approximately 70 countries worldwide.

Visit http://www.pg.com to know more.

We are an equal opportunity employer and value diversity at our company.

We do not discriminate against individuals on the basis of race, color, gender, age, national origin, religion, sexual orientation, gender identity or expression, marital status, citizenship, disability, HIV/AIDS status, or any other legally protected factor

• Bachelor's degree in Computer Science, or a related technical field, or equivalent practical experience.
• 10+ years of experience in software engineering, with a significant focus on architecture and technical leadership of large-scale, multi-tenant, or high-throughput platforms.
• Hands-on experience designing and delivering production Generative AI solutions — retrieval-augmented generation, LLM-based classification and extraction, or multi-phase agent workflows — including the schema validation, guardrails, and fallback logic that make them dependable.
• Proven experience architecting orchestration layers for distributed systems — event-driven and streaming pipelines, workflow and state management, idempotency, bounded retries, and recovery from partial failure — and applying the same discipline to AI and agent workflows.
• Strong grounding in search and retrieval: inverted indexes and lexical relevance scoring, vector and semantic similarity, hybrid retrieval and rank fusion, re-ranking, and the effect of data freshness on retrieval quality.
• Experience defining quality and evaluation practices for probabilistic systems — curated test sets, regression suites, automated and model-based scoring of output quality, and production tracing.
• Experience integrating heterogeneous enterprise systems and data sources at scale across streaming, API, and file-based patterns, with strong data modeling and schema governance instincts.
• programming skills in at least one backend language (Python, Node.js/TypeScript, or similar), with hands-on experience across document and relational data stores.
• Cloud-native engineering experience (Azure) with containerization, CI/CD pipelines, monitoring, and observability as default practice.
• Ability to lead technical design discussions, drive solution decisions, and operate as a hands-on technical lead within cross-functional and global teams.
• Strong verbal, written, and interpersonal communication skills, with the ability to collaborate effectively with technical and business stakeholders.

Preferred: Working knowledge of modern lakehouse platforms (Databricks, Delta Lake, Unity Catalog) and medallion data architectures; familiarity with AI governance, guardrails, and evaluation tooling; experience integrating enterprise systems; experience designing for regulated or highly sensitive data environments.