Source description
About the role
Job Description: Shift - 9:00 PM PHT - 6:00 AM PHT Role Summary Build multi-agent systems that turn data intelligence into automated, client-facing workflows. You will design and implement agentic architectures that make measurement models, data pipelines, and media optimization tools accessible through natural interfaces. The goal: solutions that are cheap to build, cheap to run, and easy for non-technical teams to use. Key Responsibilities Design and build multi-agent systems using LLM orchestration frameworks (LangChain, LangGraph, CrewAI, or custom)
Implement AI orchestration use cases for 4+ clients, focusing on low external dependency scenarios
Build agentic wrappers around existing data science models (MMM, forecasting, RBA, incrementality) so they can be queried and used conversationally
Set up and configure Genie spaces for client data exploration and self-service analytics
Develop tool-use patterns that connect agents to Databricks, Power BI, and other platform APIs
Write production-grade Python code with proper error handling, logging, and monitoring
Collaborate with Data Scientists to understand model inputs/outputs and build reliable agent interfaces
Participate in architecture reviews and contribute to the team's agentic design patterns and reusable components
Required Qualifications 5+ years of software engineering experience with strong Python skills
2+ year hands-on experience building with LLMs (prompt engineering, RAG, function calling, agent frameworks)
Experience with at least one agent orchestration framework (LangChain, LangGraph, AutoGen, CrewAI)
Understanding of API design, microservices, and event-driven architectures
Experience with cloud platforms (Azure preferred)
Familiarity with vector databases, embeddings, and retrieval-augmented generation patterns
Strong debugging and problem-solving skills in distributed systems
Comfort working in a fast-moving team that ships iteratively
Preferred Qualifications
-
Experience with Databricks and/or Genie
-
Background in media, advertising, or marketing technology
-
Experience building conversational interfaces or chatbot systems
-
Familiarity with MLOps practices and model serving infrastructure
-
Open-source contributions or personal projects demonstrating agentic AI work
-
Location: Makati City Brand: Merkle Time Type: Full time Contract Type: Permanent
More at Dentsu