ImpactAs a Principal Agentic Engineer in Gig Operations, you will architect and deploy Shipt’s foundational Agentic AI platform to optimize real time routing, pay, and coverage across our national fulfillment network. You will spend your days collaborating with cross functional data science, engineering, and product teams to integrate autonomous reasoning loops, tool binding frameworks, and multi agent orchestration directly into high throughput microservices. Your work directly drives the core logic that powers millions of time-critical deliveries, ensuring our autonomous workflows remain fiscally responsible, highly reliable, and compliant at scale.
What You’ll Need to Be Successful
Required Skills
10+ years of backend software development experience architecting and operating high throughput, multi region distributed microservices
Ability to lead technical discussions, communicate complex ideas and concepts simply and concisely, drive consensus and ensure projects are delivered on time
Strong mentorship abilities to ensure we evolve our staff and senior engineers into future leaders
Experience coding in one or more of the following languages: Python/Golang
Experience with SOA, microservices, and distributed architectures.
Preferred Skills
Experience in ML and DS modeling and optimization techniques
Ability to monitor and own the production services, including expertise in traditional observability tooling like DataDog.
Agentic Skills
Proven ability to build and deploy systems that use LLMs beyond simple chat interfaces
Experience with the components of intelligent systems: prompt engineering, agent definition, tool binding, reasoning loops, memory systems, and human-in-the-loop workflows.
Ability to design architectures where AI fits into complex, pre-existing production systems rather than treating LLMs as a standalone solution.
Proven experience managing Agent FinOps, including monitoring token utilization, optimizing cost-per-execution, and ensuring AI initiatives are fiscally responsible and ROI-positive.
Experience implementing robust agent lifecycle management, including agent registration, approval workflows, and role-based access control (RBAC) to ensure consistent standards for identity and compliance.
Ability to design offline and online evaluation strategies to measure agent performance, reliability, and business impact, including designing human-in-the-loop escalation triggers.
Proficiency with Google ADK, LangGraph, AutoGen, CrewAI, or similar orchestration platforms.
Familiarity with vector storage and retrieval for RAG or memory implementation.
Experience integrating AI agents with real-time signal streams (e.g., location, weather, inventory) and complex persisted data models.
Experience with monitoring tools specifically designed for tracing and debugging agentic reasoning chains (e.g., LangSmith, Langfuse etc).
Pay Range: $140,000 - $235,000
Please note that the salary range above is a guideline, and individual total compensation will vary based on factors such as qualifications, skill level, competencies, and work location.
Skills & EducationThis list includes key skills used in this job but is not inclusive of all skills needed for the role. Please see any required education below.
AI, Back-End Development, Data Science, Distributed Architectures, Microservices ArchitectureBachelor's Degree or equivalent experience| Required
Work ArrangementTo foster connection while offering continued flexibility, hybrid team members have the following in-office expectations:
Hybrid roles in Birmingham, AL typically work in-office at least 2 days per week, with core in-office days on Wednesdays and Thursdays.
Hybrid roles in Minneapolis, MN typically work in-office at least 1 day per week on either Tuesday, Wednesday, or Thursday.
Hybrid roles in San Francisco, CA typically work in-office at least 1 day per week between Monday and Thursday.
Certain roles may require in-office presence on a full-time basis. Please work with your recruiter to learn more about the classification of this role.
