Forward Deployed AI Engineer

Avenue Z•Miami, FL

1h•Onsite

About The Position

We are hiring a Forward Deployed AI Engineer to build and ship agent systems that run social commerce for the company’s brands and platform. The engineer will embed with performance media, creator and influencer, ecommerce, and analytics teams to identify lost throughput or revenue opportunities, then build and deploy production agents to address them. Example projects include keeping affiliate codes and partnership permissions active, reallocating advertising budgets toward top-performing creators, launching creator content across platforms, and reporting on what drives gross merchandise value (GMV). The role owns the full lifecycle of each solution, from discovery and architecture through development, deployment, evaluation, adoption, and ongoing operations. It involves building agent systems, integrating commerce and advertising platforms, developing data and analytics infrastructure, and measuring the business impact of systems in production.

Requirements

Computer science or another technical background, or equivalent hands-on experience as a developer or self-taught AI-native builder.
3 to 5 years building and shipping software that other people depend on.
Ability to read, write, and debug Python or TypeScript.
Experience deploying and maintaining real services and understanding how they work underneath, including services built with AI coding tools.
Hands-on experience building LLM agent systems, including function and tool calling, RAG, orchestration, prompt and context engineering, and agent evaluations.
Experience integrating third-party marketing, advertising, or commerce APIs, including familiarity with OAuth token expiry, rate limiting, webhook replay, and undocumented API behavior.
Comfort with cloud infrastructure (AWS or GCP), containers, CI/CD, and SQL.
Fluency with AI coding tools such as Claude Code and Cursor, and ability to explain, debug, and defend their output.
Understanding of performance marketing concepts such as ROAS, CAC, attribution, creative testing, funnel mechanics, and affiliate and creator economics, or ability to learn a domain quickly and demonstrate that ability.
Entrepreneurial experience building something independently, such as a startup, product, side venture, or open-source project, and ability to describe what was shipped and its results.
High agency, including gathering requirements, making decisions, and shipping without waiting for a specification, committee, or change management plan.
Ability to work with senior executives or heads of ecommerce, understand business problems, and translate them into systems.

Nice To Haves

Direct experience with TikTok Shop, Meta Ads, or Amazon Seller/Ads APIs.
Background at a DTC brand, ecommerce platform, creator or affiliate network, or performance agency.
Prior forward deployed, applied AI, or founding engineer experience.

Responsibilities

Embed with a business unit, identify where throughput or margin is lost, and ship a working agent against the problem within the first few weeks.
Build production agent systems using tool use, planning loops, memory, retrieval, orchestration, and human-in-the-loop approval gates where money or brand safety is at stake.
Integrate with commerce and advertising platforms, including TikTok Shop and TikTok Ads, Meta and Instagram, Amazon, Shopify, Google, Snap, and affiliate and creator APIs.
Build data pipelines and analytics infrastructure connecting creator content, advertising spend, and attributed GMV.
Build evaluation harnesses alongside agents and ensure production systems can be measured for correctness.
Own infrastructure including APIs, queues, authentication and token refresh, observability, error handling, rate limits, and cost controls.
Instrument systems and connect them to measurable outcomes such as hours returned, cycle time reduced, spend efficiency, GMV, or supported revenue.
Document systems, drive adoption with the teams using them, and continue improving them after launch.
Own problems end to end, including discovery, architecture, build, deployment, evaluation, adoption, and production operations.