Lead AI Engineer

Storytelling is, and will always be, the heart of what we do at Skydance. Our vision is to build a thriving entertainment ecosystem where stories and worlds are imagined, brought to life and experienced. We create for every age and audience, anchored by the strength of our content and experiences and the depth of our connection with fans. We are creator-first, audience-focused, tech-forward, globally scaled. Here, you’ll work with talented teams that move fast, think boldly and collaborate with purpose to deliver results. We aim high, champion the best ideas and win together, earning the trust of our employees, creators, partners and audiences every day. If you’re energized by the opportunity to help build the next-generation global media and entertainment company powered by creativity and technology, we’d be thrilled to welcome you aboard. LET’S GO! Overview Paramount’s Platforms & Intelligent Automation team is part of Enterprise Solutions & Technology. They create a shared AI agent infrastructure. This infrastructure supports teams in Finance, Legal & Business Affairs, Content Operations, Rights, People, and Technology. It helps these teams complete their business workflows using AI. As our Lead AI Engineer, you’ll build secure, production AI applications that orchestrate large language models, enterprise APIs, Model Context Protocol (MCP) tools and Automation Anywhere bots. Your applications will execute business workflows with human approvals, audit trails and monitoring built in. In this individual contributor role, you will work directly with business stakeholders. You will use a forward deployed model and take responsibility for applications. This means you will discover problems, develop user interfaces, coordinate with multiple agents, test the applications, deploy them, and manage operations. You’ll make application architecture, agent design, tool design and model selection decisions, while collaborating with the hiring manager and architecture review process on platform standards. Responsibilities • Architect and build secure, full stack AI applications using Python, TypeScript, APIs and React or similar user interface frameworks. Integrate LLMs, including Gemini, Claude, GPT and open weight models through Vertex AI and Azure OpenAI, with enterprise systems, MCP tool servers and Automation Anywhere A360 and Agentic Process Automation bots. Support workflows across ERP, HR, ITSM, finance close, electronic signatures and collaboration platforms. • Implement coordination across multiple agents using planner and worker, supervisor and handoff patterns with Google Agent Development Kit, Agent Engine, LangGraph or equivalent tools. Build deterministic guardrails, approval gates, role based permissions and complete audit trails so automated actions are explainable, attributable and reversible. Design state management, retries, idempotency and escalation paths for workflows that run over extended periods. • Apply enterprise security controls. Use OAuth2/OIDC and ensure service identities have the least privilege access. Manage secrets and implement defenses against prompt injection and data exfiltration, like Model Armor. Also, make sure to administer PII properly and maintain audit evidence that meets SOX requirements. Partner with Information Security, Internal Audit and Legal to define and maintain the security and production readiness checklist for agentic applications across the enterprise. • Build automated evaluation suites covering task success, groundedness, safety, latency and cost. Develop regression tests, CI/CD pipelines, OpenTelemetry tracing of agent steps, token and spend telemetry, SLOs and on call runbooks. Lead production readiness reviews and drive improvements following incidents • Partner with business process owners to identify valuable workflows, develop rapid prototypes, define success metrics and ROI, and turn pilots into supported production products. Translate requirements for offshore contractors and vendor engineers, and review their deliverables for quality and security. • Contribute reusable MCP servers, agent templates, approval interface components and evaluation harnesses to the shared platform. Create reference architectures and documentation. Mentor engineers in Enterprise Solutions & Technology. Help them understand development practices that encourage self-sufficiency. • Support ad hoc projects, including proofs of concept for executive stakeholders and evaluation of emerging models, protocols such as MCP and A2A, and vendor capabilities. Basic Qualifications • 8+ years of professional software engineering experience. • 2 years of designing and delivering production LLM applications. The applications should be used by real users on an enterprise scale. They must have features like retrieval augmented generation, tool or function calling, and agents. • Expertise in Python or be proficient in TypeScript/JavaScript. Experience in full stack development is required. This means you will create backend services and APIs, like FastAPI or Node. You should also know modern frontend frameworks such as React. It is necessary to have experience with both relational and NoSQL data stores. • Extensive functional experience with at least one major cloud platform. Google Cloud experience, including Vertex AI, Cloud Run/GKE, Pub/Sub and IAM, is preferred; AWS or Azure experience is acceptable. Experience must include Docker/Kubernetes, infrastructure as code using Terraform, and CI/CD. • Proven experience building agentic systems with orchestration across multiple steps, tool integration including MCP, state management, human approval flows, and systematic evaluation of LLM outputs for correctness, safety and cost. • Understand enterprise integration and automation. This includes knowledge of REST and GraphQL APIs. Also, knowledge of event-driven architectures, workflow and business process management concepts, and RPA platforms. Automation