AI Engineer – Build LLM-powered agents

About the role

We are seeking an AI Engineer to design, build, and deploy AI agents and LLM‑powered features for our platform. The role focuses on creating reusable components, integrating with third‑party systems, and ensuring reliable, testable agent behavior in a production environment.

Key responsibilities

• Design, develop, and launch AI agents and LLM‑driven functionalities, including prompt engineering and tool orchestration.
• Integrate AI services with external CRMs, messaging channels, and support tools using REST APIs, OAuth 2.0, and webhooks.
• Build and maintain reusable libraries such as prompt repositories, guardrails, and validation logic.
• Write typed tool contracts (e.g., with Pydantic) and enforce output schemas to keep agent behavior predictable.
• Set up and run evaluation pipelines, including trajectory and regression tests, to detect quality regressions before production.
• Collaborate with product and engineering teams to translate requirements into working agent behavior and document architecture for handoff.

Required profile

• 2–5 years of experience building production software with hands‑on LLM work.
• Strong Python development skills and familiarity with FastAPI or Flask for backend services.
• Practical experience with LLM APIs (OpenAI, Anthropic or similar) and prompt engineering.
• Knowledge of API integration patterns such as OAuth 2.0, webhooks, and REST, including async/event‑driven design.
• Experience with SQL databases and at least one vector/embedding store.
• Proficiency with Git and basic CI/CD pipelines.
• Ability to write clean, process‑oriented code and communicate technical trade‑offs to non‑technical stakeholders.

Required skills

• Python
• FastAPI
• Flask
• REST
• OAuth 2.0
• Webhooks
• SQL
• Git
• CI/CD
• Vector embedding store
• OpenAI API
• Anthropic API
• Pydantic
• Docker
• Kubernetes
• AWS
• GCP
• Azure