Lead Agentic AI Engineer

Dentsu Global Services; Mumbai; On-site; INR 6,000,000 - 9,000,000; Full time

Job summary

Dentsu Global Services in Mumbai is seeking a senior AI engineering leader to design and drive multi-agent system architectures. You will write and review production Python code, set standards, and mentor a growing team of agentic engineers in a hands‑on leadership role.

You will collaborate with data scientists to align model inputs and outputs with agent interfaces, participate in architecture reviews, and shape reusable patterns for agentic design across projects.

Qualifications

• 8-12 years of AI/engineerin g leadership experience.
• Experience architecting multi-agent systems and guiding engineering teams.
• Proficient in Python and ML/OAI tooling.
• Strong understanding of LLM orchestration frameworks.

Responsibilities

• Design and lead multi-agent system architecture for AI engineering efforts.
• Set engineering standards and best practices across the team.
• Mentor and grow agentic engineers and review code for quality and performance.
• Collaborate with data scientists to align model inputs/outputs with agent interfaces.
• Hands-on coding, reviews, and direction-setting while coordinating with leadership.

Skills

Architectural leadership

Hands-on coding

Mentoring

Team collaboration

Code review

Tools

LangChain

LangGraph

CrewAI

Databricks

Power BI

Python

Job description

Job Description

Experience - 8-12 years

Location: DGS – India (Shift- US Eastern required- 6PM-3AM )

Role Summary

Serve as the technical anchor for Dentsu's agentic AI engineering team in DGS. You will lead architecture decisions for multi-agent systems, set engineering standards, and mentor a growing team of agentic engineers. This is a hands‑on leadership role: you write code, review code, and set the technical direction while the Senior Director handles the VP-level strategy and stakeholder management.

Key Responsibilities

• Design and build multi‑agent systems using LLM orchestration frameworks (LangChain, LangGraph, CrewAI, or custom)
• 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