AI Engineering Specialist

Responsibilities

Key Responsibilities

• Build AI and ML pipelines for training, inference, embeddings, retrieval, reranking and grounded generation.
• Develop production-grade RAG solutions using appropriate chunking, vector stores, retrieval methods, metadata filters and evaluation datasets.
• Design and implement agents using frameworks such as Google ADK and LangChain, including tool use, reasoning flows, memory, caching and multi-agent orchestration.
• Integrate agents with internal APIs, search, reporting workflows, enterprise systems and external data sources using MCP or equivalent secure tool-integration patterns.
• Implement and run evaluation for accuracy, groundedness, hallucination, bias, tool success, task completion, latency, reliability and cost; add regression tests for prompt, model and workflow changes.
• Build and deploy APIs, services and applications on GCP / Vertex AI and, where required, Azure; manage containerization, CI/CD, environment configuration and release readiness.
• Monitor models and agents in production, diagnose failures, and optimize token usage, compute, latency, scalability and runtime cost.
• Collaborate with the Tech Lead, Product Owner, Data Scientists, Data Engineers and QA teams; document code, APIs, experiments, evaluations and operational runbooks

3-6 years of applied AI / ML engineering experience, with evidence of deploying models, RAG systems, agents or AI services beyond notebooks and prototypes.

• Demonstrated ownership of production code, API integration, automated testing, deployment, monitoring and troubleshooting.
• Collaborative and agile working style, with the ability to explain technical decisions and AI limitations clearly to media and product teams.
• Curiosity, structured problem solving and a strong bias toward reusable, maintainable and measurable solutions.
• Media, martech, audience data, research data or automated reporting experience is a strong plus.