Senior Automation Tester in Python; Agentic Gateway testing
Listed on 2026-10-26
-
Software Development
AI QA / Validation Engineer, AI Engineer (Applied/Software), AI Reliability/ Performance Engineer
Location: New York
We are looking for a Senior Automation Tester in Python to join our team and build an Enterprise Agent Development Platform — a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents platform standardizes agent development across the organization using Lang Graph and Strands Agents on AWS Agent Core Runtime. The initiative spans agent framework design, runtime architecture, marketplace integration, CI/CD automation, and enterprise-grade observability — reducing agent development from months to days while enforcing consistent security, quality, and governance standards.
You will own functional, security, and performance test suites for the agentic gateway.
Design and execute test suites for agentic workflows, including tool discovery, tool invocation, and multi-step agent workflows
Validate MCP protocol behavior, including tool list aggregation, tool call routing, and streaming response handling
Verify agent authorization mechanisms, including unauthorized tool access attempts and policy enforcement validation
Conduct agent performance testing covering tool discovery latency, concurrent agent sessions, and agent-to-agent latency
Build Python-based test automation using pytest with async support, mock MCP servers, and agent workflow simulation
Validate agentic observability, including trace completeness, agent step logging, and audit trail verification
Collaborate with engineering teams to define quality standards for agent framework design and runtime architecture
Support CI/CD automation efforts by integrating test suites into deployment pipelines
Requirements3+ years of QA engineering experience for AI/ML or agent systems
Hands-on experience testing AI agent systems in a production agentic AI project, such as MCP protocol testing, agent authorization/policy-enforcement testing, or multi-step agent workflow test automation
Experience testing LLM agent workflows, including tool calling and multi-step reasoning
Expertise in security testing for authorization and authentication
Skills in performance benchmarking for cloud services
Nice to have Familiarity with MCP protocol testing
Background in agent framework testing (Lang Chain, Lang Graph, Crew)
Knowledge of AWS Bedrock Agents testing
Understanding of chaos engineering for agentic systems
Familiarity with audit log validation (Cloud Trail, Open Telemetry traces)
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).