Principal AI Automation Engineer, Agentic GTM Systems

About The Role

We are building agentic workflows that operate directly inside our GTM and revenue stack. As a Principal AI Automation Engineer, Agentic GTM Systems, you will own the architecture, data and intelligence layer, and execution quality of autonomous and semi-autonomous agents that power GTM use cases such as event-based personalized communications, churn prevention, expansion, deal acceleration, and GTM intelligence. This role sits at the intersection of LLM-powered agents, Model Context Protocols (MCPs), Data warehouse, CRM systems, and GTM stack. You will work as an execution partner to the Global Head of GTM Systems, translating GTM goals into scalable, production-grade agentic systems with measurable revenue impact.

Key Responsibilities

Agentic Systems Architecture

• Design event-driven, multi-step agent workflows with reasoning, memory, and tools.
• Define standards for autonomy, guardrails, and human-in-the-loop escalation.
• Build reusable agent frameworks across churn, expansion, pipeline, and ops etc.

Data Architecture & Pipeline Engineering

• Design, build, and maintain scalable ELT/ETL pipelines that centralize data from disparate GTM sources into our data warehouse.
• Own the "Reverse ETL" process to push actionable insights from the warehouse back into frontline tools (e.g., pushing lead scores into Salesforce or churn alerts into Slack).

Model Context Protocols (MCPs) and Data warehouse integration

• Design and implement reusable MCPs that govern how agents request data, receive structured context, write back actions and outcomes for account & lifecycle context, product usage and adoption, pipeline, deal, and forecast context and customer health and revenue risk etc.
• Build secure connectors to data warehouses (Snowflake, BigQuery, Redshift, etc.), CRMs (Salesforce, HubSpot), Product, billing, and support systems etc.
• Design agent-optimized query patterns.
• Ensure data freshness, correctness, and permission-aware access.

LLM & Intelligence Layer

• Implement prompt strategies, tool calling, and RAG pipelines.
• Optimize agents for accuracy, latency, and cost.
• Build feedback loops to continuously improve agent decisions.

Reliability, Governance & Trust

• Implement observability across MCP calls, data access, and agent decisions.
• Enforce role-based access control, PII handling, and auditability.
• Reduce hallucinations and ensure consistent revenue definitions.

Preferred Experience and Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, Mathematics, or a related STEM field. A course providing deeper knowledge in AI/ML is preferred.
• 5+ years of data/AI engineering experience.
• Proven ownership of large-scale automation or AI systems.
• Hands-on with LLMs (OpenAI, Anthropic etc) and experience shipping LLM-powered applications or agents.
• Strong in Python and/or TypeScript.
• Experience with agent frameworks (LangGraph, AutoGen, CrewAI, etc.).
• Deep experience with SQL, data modeling, and warehouses.
• Familiar with event-driven architectures and workflow orchestration.
• Comfortable operating with high ambiguity and high ownership.

Key skills/competency

• AI Engineering
• Automation Systems
• LLM Integration
• Data Architecture
• GTM Systems
• Python / TypeScript
• SQL
• Agent Frameworks (LangGraph, AutoGen)
• Data Warehousing (Snowflake)
• CRM Integration (Salesforce)