Staff Software Engineer (Enterprise AI)

• As a Staff Full-Stack Software Engineer specializing in AI, you will personally design and build the AI agent capabilities and product experiences for an internal enterprise intelligence platform
• This includes the retrieval, orchestration, and reasoning layer that sits on top of a semantic data layer built and maintained by a partner data engineering team
• You’ll turn these capabilities into search, chat, and workflow experiences that help leaders find information and make decisions faster
• This is a hands-on, coding-majority role
• You’ll build the agents, prompts, tool integrations, and full-stack product surface yourself
• You’ll work directly with product owners, system leads, and domain experts across HR, Finance, IT, Legal, and Workplace to understand real workflows
• You’ll also work closely with a partner data engineering team that owns ingestion, the semantic layer, and the underlying data model
• You will consume and help shape requirements for that layer rather than building it yourself
• Your work will directly improve how Rioters hire, plan, spend, onboard, and operate at scale
• The ideal candidate is a deeply experienced full-stack software engineer who has personally shipped AI-enabled products at scale, is comfortable building in ambiguous and evolving problem spaces, and takes ownership of systems from the first commit through production operation
• The role will report to the Manager of Enterprise Systems Engineering
• Build and maintain an orchestrator + specialist-agent architecture (retrieval, tool use, structured outputs, multi-step reasoning) on top of a semantic data layer owned by a partner data team
• Design and implement retrieval and grounding for RAG/semantic search use cases: embeddings, reranking, citation of evidence, and techniques to reduce hallucination
• Integrate agents with internal and external tools/APIs (function/tool calling) to let them take real actions, not just answer questions
• Build the full-stack application layer, APIs, and UI that exposes AI-powered search, chat, and workflow experiences to end users
• Instrument AI features with observability for quality, latency, token usage, and cost, and use it to drive iteration and tuning
• Iterate on prompts and model choices quickly, with sensible fallback behavior when a model, tool, or retrieval step fails or returns low-confidence output
• Apply solid engineering fundamentals: source control, code review, automated testing (unit, integration, functional), CI/CD, and on-call for the systems you own

Benefits

• Healthcare: Medical, dental, and vision plans that cover you as well as your spouse/domestic partner and children.
• Family Care: Life insurance, parental leave, plus short and long-term disability.
• Open Paid Time Off: In addition to holidays, a 2-week end of year break, and a 1-week mid-year break, Rioters are trusted to take the time they need throughout the year.
• Retirement: Riot matches retirement contributions so you can continue to play games long after you retire.
• Play Fund: Riot’s annual play fund allows Rioters to broaden their knowledge of the games that matter to players and the community.
• Donation Matching: Riot matches donations of time and money to nonprofits to double down on support.- Experience designing and running evaluation approaches for nondeterministic systems: curated datasets, automated metrics, human review, and production feedback
• Working understanding of AI security and responsible-use risks, prompt injection, tool abuse, data leakage, access control, model limitations, sufficient to build safeguards into what you ship
• 8+ years of professional experience in full-stack software development
• Familiar with software engineering best practices: automated testing, code review, monitoring/observability, security and performance considerations
• Deep hands-on programming experience in Node, TypeScript, React
• Bachelor’s degree in Computer Engineering, Computer Science, Information Systems, or related field (or equivalent professional experience delivering enterprise technology solutions)
• Practical, end-to-end experience building RAG or agentic systems: retrieval, tool-calling, structured outputs, multi-step reasoning, and verification/evaluation loops, not just familiarity with LLM APIs
• Experience establishing basic AI observability (quality, safety, reliability, latency, token usage, cost) for features you build
• Experience with modern frameworks (e.g., NextJS, NestJS)
• Comfortable with cloud infrastructure and deployment: AWS, containers (Docker), orchestration (Kubernetes), CI/CD pipelines
• Experience building RESTful and GraphQL APIs, working with relational (e.g., PostgreSQL, MySQL) and non-relational (e.g., Redis) databases
• Deep practical knowledge of retrieval-augmented generation and semantic search, including embedding and reranking models, retrieval design, grounding, citations, and evaluation
• Experience with agent platforms (e.g., LangGraph, AutoGen, CrewAI, or comparable), vector databases, and multi-agent orchestration patterns
• Working familiarity with Python and lakehouse/data-catalog concepts (e.g., Databricks, Unity Catalog), enough to collaborate effectively with the data engineering team, without needing to own pipeline build-out
• Experience shipping an internal AI product from scratch as part of a small, fast-moving team, comfortable with a “scrappy MVP, iterate” delivery style rather than a fully-specified roadmap