Build MCP servers that securely connect AI agents and assistants to enterprise data and actions.
Develop Bedrock agents and Claude-powered workflows using AgentCore, Knowledge Bases, Guardrails, Strands Agents, or LangGraph.
Evaluate emerging AI tools, models, and patterns and turn prototypes into production services.
Design prompt and tool interactions with guardrails, human-in-the-loop approvals, evaluation, and auditability.
Build and operate AWS services and integrations using Lambda, Step Functions, API Gateway, S3, DynamoDB, EventBridge, SQS/SNS, and ECS/Fargate.
Manage AWS infrastructure with CDK, including IAM, VPC connectivity, secrets management, and deployment environments.
Develop data pipelines between enterprise applications, Redshift, and S3 for use by AI agents.
Configure CloudWatch monitoring, logs, alarms, and tracing for agents and services.
Own production systems through deployment, monitoring, incident response, and iterative improvement.
Collaborate with Finance, Accounting, and Tax stakeholders and contribute through code reviews, documentation, mentoring, and AI-assisted development.
Requirements
At least 4 years of professional software development experience.
Hands-on experience deploying and operating production workloads on AWS, including services such as Lambda, S3, Step Functions, DynamoDB, IAM, or API Gateway.
Proficiency in Python or TypeScript/JavaScript with experience shipping production code.
Experience writing, deploying, and reviewing infrastructure as code using CDK, Terraform, CloudFormation, or similar tools.
Hands-on experience with LLM APIs such as Amazon Bedrock or the Anthropic API, including prompt design, tool calling, and structured outputs.
Working knowledge of MCP, agent frameworks, RAG patterns, and model-selection trade-offs.
Experience designing, testing, and debugging APIs using REST, JSON, and OpenAPI, with tools such as Bruno or Postman.
Understanding of OAuth 2.0 authorization flows and OpenID Connect for securing APIs and agent-to-service access.
Preferred qualifications include AWS certification and production experience with MCP servers, Bedrock agents, AgentCore, Strands Agents, or LangGraph.
Preferred qualifications include LLM evaluation, observability, guardrails, RAG, vector stores, internal developer tooling, Finance domain knowledge, enterprise systems integration, or SAP development using ABAP or OData.
Benefits
Medical, dental, vision, disability, prescription, life, and AD&D insurance options.
401(k) and 401(k) matching.
Maternity, parental, adoption, and surrogacy reimbursement benefits.
Flexible paid time off and an Amazon employee discount.
Employee assistance, mental health support, medical advice line, and flexible spending accounts.
Position based in San Francisco, California.
Salary: $165k - $224k/yr
Twitch
Twitch is where thousands of communities come together for whatever, every day. Together for streamers. Together for games we love. Together for each other.