AI Engineer – LLM Applications & Agent Platform

About the role

We are looking for an AI Engineer to lead the design, development, and improvement of our internal AI‑powered agent platform. The role focuses on integrating large language models with internal tools, databases, and marketing APIs to boost productivity across the organization.

Key responsibilities

• Design, build, and maintain AI applications that leverage LLM APIs, tool calling, and structured JSON outputs.
• Develop agent architectures that integrate SQL execution, Python code execution, and advertising platform APIs.
• Implement multi‑turn context handling, session memory strategies, and prompt structures to reduce hallucinations.
• Create safeguards and guardrails for tool execution, SQL queries, and code runs, including retry logic and validation.
• Contribute to structured evaluation frameworks, regression testing, and task‑based success metrics.
• Support expansion of the platform into document generation, slide decks, and Google Workspace integrations.
• Collaborate with ML engineers, product managers, and full‑stack engineers to ensure robustness and alignment with business goals.
• Stay current with advances in LLM systems and agent architectures to continuously improve capabilities.

Required profile

• Strong Python programming experience with production‑grade systems.
• Hands‑on experience building applications using LLM APIs such as OpenAI, Anthropic, or Vertex AI.
• Deep understanding of context windows, multi‑turn conversations, tool/function calling, and structured JSON outputs.
• Proficiency in integrating external APIs and working with SQL databases.
• Experience with cloud platforms (GCP, AWS, or Azure).
• Excellent problem‑solving, debugging, and cross‑functional communication skills.

Required skills

• Python
• LLM APIs (OpenAI, Anthropic, Vertex AI, etc.)
• SQL
• Cloud platforms (GCP, AWS, Azure)