Haystack
← Back to Jobs
Technology
DE

AI SDET

Delviom LLCSunnyvale, CA🇺🇸United StatesPosted 2 Sept 2026

Why This Role Stands Out

As an AI SDET at Delviom LLC, you'll pioneer cutting-edge AI-driven test automation, directly shaping the future of quality assurance in a dynamic tech environment. This role is perfect for a seasoned QA professional with a passion for AI and machine learning, eager to build self-healing frameworks and validate sophisticated LLMs. Embrace this opportunity to significantly contribute to a reputable company and elevate your expertise in a high-demand field.

Quick Overview

Seniority
Mid Senior
Work mode
On Site
Location
Sunnyvale, CA, United States
Posted
23 hours ago
DockerMicroservicesSQLScalaAWSMLOpsAzureJavaLLMPlaywrightPython

Job Description

Role: AI SDET

Location: Sunnyvale, CA, Onsite

Duration: 12+ Months

Job Summary:

We are seeking an innovative AI Software Development Engineer in Test (AI-SDET) to join our client s quality engineering team. An ideal candidate would bridge the gap between traditional QA and artificial intelligence by designing self-healing test automation frameworks, validating Large Language Models (LLMs), and integrating AI agents into CI/CD.

Experience Required:

6 to 8 years of hands-on experience in software quality engineering, test automation and AI ML development.

Qualifications/Required Skills:

  • Bachelor s degree in computer science, or a related field.
  • Proficiency in Python/Java/Scala.
  • Proficiency with modern tools - Playwright.
  • Experience with LLM APIs (e.g. Claude, OpenAI) and agent frameworks (e.g. LangChain)
  • Cloud-based platforms with AI integration ( Azure Open AI, AWS Open AI)
  • Strong understanding of CI/CD pipelines and containerization (Docker).
  • Strong experience validating complex RESTful APIs, microservices and databases (SQL/NoSQL).
  • Experience with Retail Domain is preferred, not a constraint though
Key responsibilities:
  • AI Framework Architecture: Architect and maintain enterprise-grade, scalable automation frameworks.
  • GenAI and Agentic automation: Build intelligent test agents, automated prompt-engineering validators, and self-healing test execution scripts.
  • Model and Evals validation: Design and maintain evaluation frameworks covering hallucination detection, roundedness, toxicity, bias and safety guardrails.
  • Synthetic Data Generation: Design AI-driven data generation pipelines to simulate complex, production-like testing scenarios.
  • ML Pipeline testing: Validate RAG (Retrieval-Augmented Generation) architectures, embedding quality, retrieval accuracy, and vector search relevance.
  • Intelligent testing: Build smart test selection and impact analysis systems that predict which test suits to run based on specific code changes.
  • Framework Development: Develop and enhance scalable, robust automation scripts for UI, API, and backend validation using modern languages and frameworks.
  • CI CD Integration: Work alongside MLOps teams to build continuous testing and automated verification pipelines.
Behavioral Skills:
  • Strong analytical and problem-solving skills with a passion for adoption new AI Technologies.
  • Excellent Communication skills and collaboration skills
  • Ability to propose and implement improvements in the system
  • Ability to work with cross-functional stakeholders

Similar jobs