Software Engineer II, Fintech

Twitch•San Francisco, CA

9h•$165,200 - $223,600

About The Position

Twitch's Enterprise Platform & Technology organization is seeking a Software Development Engineer II to build agentic AI systems on AWS for Finance and enterprise functions across Twitch and Amazon. This hands-on role involves designing and shipping MCP servers, Bedrock-based agents, and Claude-powered workflows, as well as owning their AWS-native infrastructure end to end. The engineer will connect AI agents to enterprise systems and data, automate operational work, and deliver reliable, secure, observable services. The role combines modern AI tooling with production cloud engineering and includes evaluating emerging tools and models, advancing team automation, and turning prototypes into production services. The position collaborates with Finance, Accounting, and Tax stakeholders to translate business needs into AI-driven solutions. It also owns production systems from deployment and monitoring through incident response and ongoing improvement, and supports the team through code reviews, documentation, mentoring, and AI-assisted development.

Requirements

Demonstrated heavy daily use of AI tools such as Claude, Claude Code, Kiro, Amazon Q Developer, or similar for code generation, data analysis, automation, and problem-solving.
Hands-on experience building with LLM APIs such as Amazon Bedrock or Anthropic API, including prompt design, tool calling, and structured outputs.
Working knowledge of current AI tooling, including MCP, agent frameworks, RAG patterns, and model-selection trade-offs.
At least 4 years of professional software development experience.
Hands-on experience deploying and operating production workloads on AWS, using services such as Lambda, S3, Step Functions, DynamoDB, IAM, or API Gateway.
Proficiency in Python or TypeScript/JavaScript and a track record of shipping production code.
Experience writing, deploying, and reviewing infrastructure as code, such as CDK, Terraform, or CloudFormation, in a team setting.
Experience designing, testing, and debugging REST, JSON, and OpenAPI APIs using tools such as Bruno or Postman, including building request collections, handling authentication flows, and validating response contracts.
Understanding of OAuth 2.0 authorization flows, including authorization code and client credentials, and OpenID Connect (OIDC) for securing APIs and agent-to-service access.

Nice To Haves

AWS certification, such as 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 such as AgentCore, Strands Agents, or LangGraph.
Experience with LLM evaluation, observability, and guardrails, including hallucination checks, cost and latency optimization, and prompt versioning.
Experience with RAG and vector stores such as 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 such as AP, AR, GL, reconciliations, or payouts.
Experience integrating with enterprise systems such as ERP, procurement, or payments platforms.
Experience with SAP development, including ABAP, OData, or integrations.

Responsibilities

Build MCP servers that provide AI agents and assistants secure access to enterprise data and actions, including through Bedrock AgentCore Gateway.
Build Bedrock agents and Claude-powered workflows to automate Finance work such as reconciliations, reporting, variance analysis, and payouts.
Evaluate and adopt new AI tools, models, and patterns, and turn prototypes into production-grade services.
Design for safety and trust through prompt and tool design, guardrails, human-in-the-loop approvals, evaluation, and auditability.
Build and operate AWS services for agents and integrations, including Lambda, Step Functions, API Gateway, S3, DynamoDB, EventBridge, SQS/SNS, and ECS/Fargate.
Manage infrastructure with CDK, including CI/CD, IAM, VPC connectivity, secrets management, and beta, gamma, and production environments.
Develop data pipelines between enterprise applications, Redshift, and S3, and make the data available to AI agents.
Set up monitoring for agents and services using CloudWatch metrics, logs, alarms, and tracing.
Collaborate with Finance, Accounting, and Tax stakeholders to translate business requirements into AI-driven solutions.
Own production systems end to end, including deployment, monitoring, incident response, and iterative improvement.
Raise the team's bar through code reviews, documentation, mentoring, and promotion of AI-assisted development.