Lead Software Engineer - AI Automation

AI Automation Engineer

Let’s be unstoppable together!

At Circana, we are fueled by our passion for continuous learning and growth, we seek and share feedback freely, and we celebrate victories both big and small in an environment that is flexible and accommodating to our work and personal lives. We have a global commitment to diversity, equity, and inclusion as we believe in the undeniable strength that diversity brings to our business, employees, clients, and communities. With us, you can always bring your full self to work. Join our inclusive, committed team to be a challenger, own outcomes, and stay curious together. Circana is proud to be Certified™ by Great Place To Work®. This prestigious award is based entirely on what current employees say about their experience working at Circana.

Learn more at www.circana.com (http://www.circana.com)

Role Overview

We are looking for an AI Automation Engineer to join Circana’s AI & Automation transformation program. In this role, you will build and ship production automations that integrate Python, REST APIs, data stores, and Large Language Models into end-to-end solutions across Circana’s global Operations Division. This is a hands-on engineering role where you will take process specifications and turn them into deployed, monitored, production systems — working in short-cycle sprint pods that deliver a working automation within a single quarter. The program targets millions in run-rate cost savings across 17 operational value stream areas, and you will be a core part of making that happen.

Job Responsibilities

• Take process specifications from the Solutions Architect function and design the technical approach, including data flow, integration points, LLM components, error handling, and human-in-the-loop touchpoints.
• Build automations in Python: REST API calls, data store reads and writes, transformation logic, LLM integration, output validation, and the orchestration that ties it together.
• Integrate LLMs into production workflows — including prompt engineering, structured output parsing, and output validation against defined quality thresholds.
• Write tests that cover core logic, integration with external dependencies, and output quality checks for LLM components against defined acceptance criteria.
• Deploy solutions to production, monitor initial runs, and manage hypercare through to stable operation.
• Contribute to the program’s shared patterns library and component library as reusable patterns emerge across automation projects.
• Maintain code in a shared repository with branching, pull request review, and documentation standards established by the programme.
• Participate in sprint ceremonies (planning, daily standup, review, retrospective) and surface blockers early and constructively.
• Build lightweight full-stack tooling (React frontends, FastAPI backends) when automations require a human-facing interface such as review queues, exception dashboards, approval workflows, or configuration surfaces.
• Contribute to the design and implementation of multi-step agentic workflows, including tool use, memory, planning, and evaluation frameworks as the programme’s agentic automation capability matures.
• Hand off completed automations to operations teams with documentation that a non-engineer can follow.

Requirements

• 6+ years of Python development experience in a production environment — systems that run, fail, get fixed, and run again, not scripts on a laptop.
• Solid REST API integration experience: authentication patterns, rate limiting, pagination, error handling, and the debugging skills to diagnose integration failures without documentation.
• Working knowledge of relational and cloud data stores (PostgreSQL, Snowflake, S3/Blob storage): SQL for querying and writing, and enough understanding of schema to navigate one you did not design.
• Direct experience integrating Large Language Models into production workflows: prompt engineering, structured output parsing, output validation, and the discipline to handle hallucination as an engineering problem.
• Git proficiency: branching strategy, pull request discipline, meaningful commit messages, and the ability to review code constructively.
• The ability to read a process specification and ask the right questions before writing a line of code — identifying what is undocumented, what assumption is doing the most work, and where things will break first.
• Familiarity with agile deliver…