AI Engineering Lead

Primetag; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Fully remote with EU hours

Comprehensive medical insurance

Nomad-style offices for collaboration

Job summary

Primetag seeks a senior AI Platform Engineer to lead the technical direction of an agentic AI platform for the creator marketing space. The role focuses on scaling retrieval systems, defining architecture, improving quality and cost efficiency, and shaping future product capabilities, with room to grow into broader team leadership over time.

You will work fully remotely with flexible core hours aligned to European time, collaborate with Product and the AI squad to unblock work and align on

Qualifications

• Senior-level experience designing and operating AI or ML systems at scale.
• Deep knowledge of retrieval-augmented generation, embeddings, and large language model architectures.
• Strong engineering background in Python and modern backend or data systems.
• Track record of shipping production AI products with measurable quality and cost outcomes.
• Ability to operate hands-on while influencing broader technical direction.

Responsibilities

• Scale retrieval systems across billions of data points and multi-tenant use cases.
• Build agentic workflows, knowledge bases, real-time data synthesis, and MCP integrations.
• Set the technical bar for AI engineering: quality, reliability, and cost optimization.
• Evaluate initiatives by customer value, cost, and strategic impact.
• Collaborate with Product and AI squads to unblock work and align on roadmaps.

Skills

AI/ML systems at scale

RAG and embeddings

LLM architectures

Python programming

Backend/data systems

Production AI delivery

Hands-on leadership

Tools

Python

Job description

Role overview

This senior, hands-on position leads the technical direction of an agentic AI platform built for the creator marketing space. The role focuses on scaling retrieval systems, defining architecture, improving quality and cost efficiency, and shaping future product capabilities, with room to grow into broader team leadership over time.

Responsibilities

• Scale existing RAG systems by optimizing retrieval across billions of data points, millions of creators, and complex multi-tenant use cases
• Build new capabilities including agentic workflows, client‑specific knowledge bases, real‑time data synthesis, and MCP integrations
• Set the technical bar for AI engineering, driving quality, reliability, and cost optimization across the stack
• Evaluate technical initiatives through customer value, cost, and strategic impact rather than engineering elegance alone
• Partner closely with Product and the AI squad to unblock work and align on roadmap priorities

Requirements

• Senior‑level experience designing and operating AI or machine learning systems at scale
• Deep knowledge of retrieval‑augmented generation, embeddings, and large language model architectures
• Strong engineering background in Python and modern backend or data systems
• Track record of shipping production AI products with measurable quality and cost outcomes
• Ability to operate hands‑on while influencing broader technical direction

Benefits and work setup

• Fully remote role with flexible core hours within European time (9am-6pm, 4 required hours per day)
• Comprehensive medical insurance for all team members
• Periodic nomad‑style offices set up across European locations for in‑person collaboration