Senior Director of Agentic AI Engineering & Platform Architecture

Circana

12h•Remote

About The Position

We are seeking a Head of Agentic AI Engineering & Platform Architecture (Director or Sr Director) to lead the design, development, and scaling of our next-generation Agentic AI onboarding and analytics acceleration platform. This role combines principal-level architecture, hands-on engineering leadership, and client-facing technical ownership. You will set the multi-year strategy for agentic automation, autonomous AI capabilities, metadata-driven ingestion, supervised learning reinforcement, and large-scale distributed processing. The ideal leader is deeply technical, product-oriented, and passionate about building real, production-grade multi-agent systems, not prototypes. Success is measured by: Faster client onboarding Reduction in delivery rework Platform adoption across teams System reliability, scalability, and performance Engineering excellence and velocity

Requirements

15+ years in software engineering, AI/ML, data engineering, or distributed systems
5+ years in senior/principal/staff engineering, architect, or platform leadership roles.
3+ years leading engineering teams.
Experience operating in client-facing, delivery-oriented, or consulting environments.
Expertise with agentic AI frameworks such as LangChain, LangGraph, AutoGen
Deep experience with RAG, tool/function calling, prompt engineering, multi-step reasoning, and context engineering.
Hands-on experience building autonomous agent capabilities: memory architectures, reflection/self-critique loops, planning/decomposition, multi-agent coordination, and state management.
Proficiency with Knowledge Graph / GraphDB and vector databases.
Strong programming skills in Python (production services, performance patterns, concurrency).
Expertise with Apache Spark for distributed pipelines, onboarding ETL/ELT, schema enforcement, and performance tuning.
Strong proficiency in SQL, data modeling, metadata design, and analytics/warehouse patterns.
Experience architecting distributed ingestion and workflow systems (batch + streaming), including robust data quality patterns.
Experience with LLMOps, MLOps, and AIOps platforms.
Exceptional communicator with ability to influence executive, client, and engineering audiences.
Demonstrated success driving adoption, productization, and operational rigor.
Must be product-oriented: focuses on durable, scalable solutions rather than one-off prototypes; ensures production readiness, user adoption, and alignment with long-term platform strategy.

Nice To Haves

Familiarity with modern front-end frameworks (e.g., React) a plus.

Responsibilities

Serve as the principal architect for Circana’s agentic AI platform, defining system architecture, integration patterns, and technical strategy.
Lead design of multi-agent orchestration, context management, and distributed onboarding pipeline.
Own evolution of Context Studio and metadata-driven automation frameworks.
Ensure scalability, reliability, security, and cost efficiency across AI and data pipelines.
Build Autonomous Agent Architecture that includes agent memory systems (working, long-term, semantic), self‑evaluation/reflection loops and reasoning‑improvement mechanisms, planning & task decomposition capabilities, multi-agent coordination, guardrails and governance policies.
Establish and maintain the multi-year platform roadmap, including next-generation automation agents, quality gate pipelines, and insight storytelling components.
Must be product-oriented: focuses on durable, scalable solutions rather than one-off prototypes; ensures production readiness, user adoption, and alignment with long-term platform strategy.
Partner closely with Product on prioritization, customer validation, UX integration, and cross-team adoption.
Establish enterprise AI governance controls to ensure agentic systems operate within policy, regulatory, privacy, and data‑minimization boundaries, based on best‑practice governance patterns for agentic AI.
Implement agent observability (decision logs, audit trails, monitoring dashboards) and behavioral tracking to maintain visibility into agent actions and prevent unintended data or system access. 3
Integrate AI security measures to protect against misuse, privilege escalation, and unauthorized agent actions.
Apply AIOps-based monitoring and LLMOps/MLOps operational practices (evaluation, drift monitoring, reproducibility, lifecycle automation) to ensure reliability, safety, and high‑quality outputs across all agent workflows
Lead design and build-out of multi-agent automation, Spark-based ingestion, RAG pipelines, context management, and supervised learning reinforcement loops.
Need to be hands-on building complex platform components, providing direct contributions in Python, Spark, LangChain, orchestration frameworks, and agent toolchains.
Serve as the primary AI expert in client onboarding automation, shaping solutions, architectural proposals, and automation strategies.
Communicate complex design decisions and trade-offs clearly to both technical and non-technical stakeholders.
Drive adoption during onboarding programs, ensuring measurable improvements in onboarding speed, quality, and rework reduction.
Support pre-sales discussions, solution architecture reviews, and executive briefings.
Build and lead a high-performance engineering team, including US-based technical leaders and offshore engineering teams.
Mentor engineers in LLM engineering, agent architectures, distributed systems, metadata automation, and LLM/AI operationalization.
Partner cross-functionally with Product, Delivery, Analytics, Data Engineering, and Platform Engineering.