About the role
About Us
Twitch is the world’s biggest live streaming service, with global communities built around gaming, entertainment, music, sports, cooking, and more. It is where thousands of communities come together for whatever, every day.
We’re about community, inside and out. You’ll find coworkers who are eager to team up, collaborate, and smash (or elegantly solve) problems together. We’re on a quest to empower live communities, so if this sounds good to you, see what we’re up to on LinkedIn and X, and discover the projects we’re solving on our Blog. Be sure to explore our Interviewing Guide to learn how to ace our interview process.
About the Role
Twitch's Enterprise Platform & Technology (EPT) organization is looking for a Software Development Engineer II to build agentic AI systems on AWS that power Finance and enterprise functions across Twitch and Amazon. This is a hands-on engineering role where you'll design and ship MCP (Model Context Protocol) servers, Bedrock-based agents, and Claude-powered workflows, and own the AWS-native infrastructure behind them end-to-end (Lambda, Step Functions, API Gateway, S3, DynamoDB, ECS/Fargate, CDK).
You'll work at the intersection of modern AI tooling and production cloud engineering, connecting AI agents to enterprise systems and data, automating manual operational work, and turning emerging AI capabilities into reliable, secure, observable services. The business problems are well understood; how you solve them with AWS + AI is up to you. We're looking for an engineer who stays current with the AI tooling landscape (models, agent frameworks, coding assistants, MCP), uses these tools heavily every day, and raises the bar on automation for the whole team.
You Will
Build agentic AI systems
- Build MCP servers that give AI agents and assistants (Claude, Amazon Q, Kiro, and internal tools) secure access to enterprise data and actions, including through Bedrock AgentCore Gateway
- Build Bedrock agents and Claude-powered workflows (using AgentCore, Knowledge Bases, Guardrails, Strands Agents, or LangGraph) that automate Finance work like reconciliations, reporting, variance analysis, and payouts
- Evaluate and adopt new AI tools, models, and patterns as they emerge; turn prototypes into production-grade services
- Design for safety and trust through prompt/tool design, guardrails, human-in-the-loop approvals, evaluation, and auditability