Principal Engineer

Shipt•Minneapolis, AL

2d•Hybrid

About The Position

As 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.

Requirements

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.
AI, Back-End Development, Data Science, Distributed Architectures, Microservices Architecture
Bachelor's Degree or equivalent experience

Nice To Haves

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.
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.
Proficiency with Google ADK, LangGraph, AutoGen, CrewAI, or similar orchestration platforms.
Familiarity with vector storage and retrieval for RAG or memory implementation.
Experience with monitoring tools specifically designed for tracing and debugging agentic reasoning chains (e.g., LangSmith, Langfuse etc).

Responsibilities

Architect and deploy Shipt’s foundational Agentic AI platform to optimize real time routing, pay, and coverage across our national fulfillment network.
Collaborate 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.
Drive the core logic that powers millions of time-critical deliveries, ensuring autonomous workflows remain fiscally responsible, highly reliable, and compliant at scale.
Lead technical discussions, communicate complex ideas and concepts simply and concisely, drive consensus and ensure projects are delivered on time.
Mentor staff and senior engineers to evolve them into future leaders.
Monitor and own production services.
Design architectures where AI fits into complex, pre-existing production systems rather than treating LLMs as a standalone solution.
Manage Agent FinOps, including monitoring token utilization, optimizing cost-per-execution, and ensuring AI initiatives are fiscally responsible and ROI-positive.
Implement robust agent lifecycle management, including agent registration, approval workflows, and role-based access control (RBAC) to ensure consistent standards for identity and compliance.
Design offline and online evaluation strategies to measure agent performance, reliability, and business impact, including designing human-in-the-loop escalation triggers.
Integrate AI agents with real-time signal streams (e.g., location, weather, inventory) and complex persisted data models.