Senior AI Engineer, Applied AI Solutions

About the role

Horizon Media is building an applied AI team that turns business workflows into production agent systems. As a Senior AI Engineer you will design, build and run multi-agent solutions on Google Cloud, from first prototype to a platform other teams build on. The role needs strong software engineering fundamentals, sound judgment about what a model should and should not do, and the ability to work directly with business stakeholders in ambiguous situations.

Key responsibilities

• Design and build multi-agent systems with Google Agent Development Kit (ADK), using orchestrator, sub-agent, sequential and agent-as-tool patterns, and deploy them to Vertex AI Agent Engine.
• Break business workflows into steps handled by models and steps handled by deterministic code, and add human-in-the-loop controls, grounding and output checks.
• Build MCP servers and A2A services that expose enterprise systems to agents, and integrate agents with BigQuery, Cloud SQL, Cloud Storage, Vertex AI Search, Microsoft 365, SharePoint and Microsoft Graph.
• Select and combine models across providers, including Gemini and Claude on Vertex AI Model Garden, with tiering and escalation.
• Design permission-aware systems with least-privilege access, Workload Identity Federation, Secret Manager and OAuth, and defend against prompt injection.
• Build evaluation suites with golden datasets, deterministic assertions and regression comparisons, enforced through automated tests and CI gates.
• Build reusable platform components, operate GitOps deployment pipelines, deploy on Cloud Run and Vertex AI Agent Engine, and instrument agents with logging, tracing and cost tracking.
• Work with business leaders to map workflows and define success metrics, write design documents, lead solutions from prototype through UAT to production, and run experiments to recommend adoption.

Required profile

• 5+ years of software engineering experience, including 2+ years building and operating LLM-based applications in production.
• Production experience on Google Cloud, including Vertex AI, Gemini models, Cloud Run, BigQuery, IAM and Secret Manager.
• Experience designing evaluation for LLM systems, including golden datasets, automated checks and regression testing.
• Working knowledge of how large language models are trained, evaluated and served, including tokenization, embeddings, fine-tuning and inference settings.
• Solid fundamentals in data structures, algorithms, concurrency and failure handling.
• Ability to translate business problems into technical designs and explain trade-offs to technical and non-technical audiences.

Required skills

• Strong Python, including typed code, pytest, Pydantic and API/microservice development.
• Hands-on experience building agentic systems with tool use and multi-step orchestration (Google ADK, LangGraph, LlamaIndex or similar).
• Docker, CI/CD pipelines and infrastructure as code.
• Nice to have: Vertex AI Agent Engine, MCP servers, A2A services, Claude or other model providers, Microsoft 365 integration, TypeScript or Node.js, and internal developer platform experience.

What we offer

• Salary range of $195,000 - $225,000, with actual base pay depending on skills, experience and qualifications.
• Discretionary bonus and benefits including health, life and disability insurance, retirement savings plans, company-paid holidays and unlimited PTO, mental health and wellness resources, pet insurance, childcare resources, identity theft insurance, fertility assistance and fitness reimbursement.