Software Engineer II, Fintech

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

Build on AWS

• Build and run the AWS services that host the agents and integrations (Lambda, Step Functions, API Gateway, S3, DynamoDB, EventBridge, SQS/SNS, ECS/Fargate)
• Manage infrastructure with CDK, including CI/CD, IAM, VPC connectivity, secrets management, and beta/gamma/prod environments
• Develop data pipelines between enterprise apps, Redshift, and S3, and make that data available to AI agents
• Set up monitoring for agents and services (CloudWatch metrics, logs, alarms, tracing)

Cross-cutting

• Collaborate with Finance, Accounting, and Tax stakeholders to translate business requirements into AI-driven solutions
• Own production systems end-to-end, from deployment and monitoring to incident response and iterative improvement
• Raise the team's bar through code reviews, docs, mentoring, and promoting AI-assisted development

You Have

AI and Agents

• Demonstrated heavy use of AI tools (Claude, Claude Code, Kiro, Amazon Q Developer, or similar) integrated into your daily engineering workflow for code generation, data analysis, automation, and problem-solving
• Hands-on experience building with LLM APIs (Amazon Bedrock, Anthropic API, or similar), including prompt design, tool calling, and structured outputs
• Working knowledge of the current AI tooling landscape, including MCP, agent frameworks, RAG patterns, and model selection trade-offs

AWS and Engineering

• 4+ years of professional software development experience
• Hands-on experience deploying and operating production workloads on AWS (Lambda, S3, Step Functions, DynamoDB, IAM, API Gateway, or similar)
• Proficiency in Python or TypeScript/JavaScript with a track record of shipping production code
• Experience writing, deploying, and reviewing infrastructure-as-code (CDK, Terraform, or CloudFormation) in a team setting

• Experience designing, testing, and debugging APIs (REST, JSON, OpenAPI) using tools like Bruno or Postman, including building request collections, handling authentication flows, and validating response contracts
• Understanding of OAuth 2.0 authorization flows (authorization code, client credentials) and OpenID Connect (OIDC) for securing APIs and agent-to-service access

Bonus Points

• AWS certification (e.g., Solutions Architect, Developer, DevOps Engineer, Machine Learning Engineer, or AI Practitioner)
• Experience shipping MCP servers, Bedrock agents, or other agentic systems to production, using tools like AgentCore, Strands Agents, or LangGraph
• Experience with LLM evaluation, observability, and guardrails (hallucination checks, cost/latency optimization, prompt versioning)
• Experience with RAG and vector stores (Bedrock Knowledge Bases, OpenSearch Serverless, pgvector, or S3 Vectors)
• Experience building internal developer tooling or AI assistants used by other engineers
• Finance domain knowledge in areas like AP, AR, GL, reconciliations, or payouts
• Experience integrating with enterprise systems (ERP, procurement, payments platforms)
• Experience with SAP development (ABAP, OData, or integrations)

Job ID: TW9266