Principal, System Engineer 2, Multi-Agent AI, AdTech

This is a New York City, NY, based position that works both in-office (2 days/week) and remotely. #LI-Hybrid DIRECTV is seeking a Principal, System Engineer 2 to design, build, and operationalize sophisticated agentic AI systems across our Advertising Technology ecosystem. This is a senior individual contributor assignment for a hands-on systems engineer who can move between architecture, production code, platform services, and direct engagement with business users.    The ideal candidate brings broad experience across AI, distributed systems, backend engineering, data, product delivery, and enterprise integration. This person will provide end-to-end technical ownership for secure multi-agent systems and collaborative AI work environments where business users and agents can plan, reason, use tools, share context, and complete complex advertising and media workflows.    Here's what you'll do:   Multi-Agent System Architecture & Development   Design and build production multi-agent systems, including planners, coordinators, specialist agents, reviewers, human approval points, shared state, memory, and recovery paths.  Define orchestration patterns for agent delegation, task decomposition, consensus, tool selection, and deterministic workflow control.  Write production code and reference implementations, not just architecture diagrams, prototypes, or prompt specifications.  Evaluate model, framework, and runtime tradeoffs while keeping solutions modular and avoiding unnecessary vendor lock-in.    Collaborative AI Work Environments   Build collaborative workspaces where business users and multiple agents can jointly investigate, plan, create, review, and execute work.  Design shared-context patterns such as workspaces, case files, task state, artifacts, approvals, audit history, and role-aware memory.  Create experiences that make agent evidence, tool activity, decisions, and handoffs understandable to business users.  Enable reusable skills and workflows across campaign planning, operations, analytics, incident response, and engineering use cases.    Backend Services, Tools & Enterprise Integration   Design and develop backend services, APIs, event-driven workflows, tool registries, and integration services that connect agents to enterprise capabilities.  Build governed tool interfaces using MCP-style patterns, strong schemas, identity propagation, authorization, validation, rate limits, and auditability.  Integrate agent systems with advertising platforms, data services, Snowflake, operational systems, content repositories, and third-party APIs.  Apply distributed-systems practices for reliability, idempotency, retries, timeouts, fallbacks, concurrency, and state management.    Context Engineering for Business Users   Design context strategies combining user intent, role, workflow state, enterprise knowledge, structured data, tool outputs, conversation history, and policy constraints.  Build…