AI SDET (NO C2C)

No Sponsorship. NO C2C. Onsite from day one.

We are looking for a AI Quality Engineer with strong automation expertise and hands-on experience validating LLMs, GenAI workflows, and AI-driven applications. This role involves building automated test suites, validating AI outputs, ensuring system reliability, and contributing to the quality strategy for next-generation AI features.

Core Experience

• 4-6 years as a Software Engineer, SDET, or Automation Engineer.
• Strong coding skills in Python, TypeScript, or Java.
• Hands-on experience developing automation scripts, tools, or frameworks.
• Practical experience using LLMs, prompt engineering, and evaluating AI-generated outputs.
• Familiarity with agentic AI systems and exposure to tools like LangGraph, AutoGen, or CrewAI.
• Basic understanding of Model Context Protocol (MCP) or context-aware workflow automation (nice to have).

AI / ML Technologies

• Practical experience with AI/ML frameworks:
• LangChain, Hugging Face, GPT models, vector databases, RAG pipelines.
• Experience with ML/DL libraries such as:
• Scikit-learn, PyTorch, TensorFlow, Keras, Transformers, OpenCV.
• Ability to work with embeddings, similarity search, and content evaluation metrics.

GenAI & AI Agent Development

• Ability to integrate or build GenAI components, including RAG pipelines or agent-based workflows.
• Support model evaluation tasks such as:
• Output quality checks
• Hallucination detection
• Prompt validation
• Regression checks for model updates

Automation & Quality Engineering

• Experience building automation using Python, PyTest, Selenium, Playwright, or API testing libraries.
• Ability to design and execute automated tests for:
• Functional
• Integration
• API
• Basic performance & reliability testing
• Hands-on experience testing RESTful APIs and building automated API suites.

Cloud, DevOps & CI/CD

• Exposure to deploying AI or automation solutions on AWS.
• Working knowledge of CI/CD pipelines, including:
• Automated testing
• Model validation steps
• Versioning & artifact management

SDLC & Collaboration

• Strong understanding of the software development lifecycle, including requirements, development, testing, and defect analysis.
• Ability to collaborate with Developers, Data Scientist, and QE teams, clearly communicating progress, risks, and results.
• Skilled in documenting and tracking defects and participating in defect triage.