Software Engineer – AI Quality & Test Automation | Security - Python | Golang | Test Automation | AI/ML Testing | Performance Testing | Security Testing | LLM APIs | Agentic Workflows | LangChain | LangSmith | Contract Testing | Playwright (8 - 12 Years)

Develop and maintain test infrastructure and benchmarking protocols for AI-agentic Security Operations Center (SOC) focused on ensuring system reliability and performance.

Translate quality challenges into technical solutions through AI-based testing methodologies and agent development, including implementing proof-of-concept experiments and validation techniques such as LLM-as-judge and tenant isolation probes.

Collaborate cross-functionally with engineering teams to integrate contract testing, audit log validation, and security compliance within the software development lifecycle.

Bachelor’s degree in a relevant field.

8+ years of software development and test automation experience, including building large-scale testing ecosystems.

Proficiency in Python and Go programming languages, with experience designing scalable and maintainable testing infrastructure.

Demonstrated experience with security compliance frameworks, modern performance testing methodologies, and using AI to build test automation.

Experienced in AI/ML testing with skills in LLM APIs (e.g., Claude, Codex), prompt engineering, LangChain, and LangSmith for model reliability and AI behavioral regression.

Strong background in security and compliance validation tools, such as Open Cybersecurity Schema Framework (OCSF), Caldera, vacuum linter, tenant isolation probes, and audit log validation.

Skilled in test automation frameworks (including contract testing and Playwright) and modern performance testing tools like K6, Terra Virtual Machine, and JMeter.