SDET – AI First Quality Engineer

TidyHire; Hyderabad; Sur place; INR 900 000 - 1 300 000; Plein temps

Résumé du poste

TidyHire is seeking an SDET – AI-First Quality Engineer in Hyderabad to design and build autonomous testing systems powered by LLMs and agents.

You will create AI agents for test scenario generation, integrate APIs and data stores, and collaborate with Product, Dev, and QA to push AI-first QE across the stack.

Experience with Python, LangChain, RAG, and cloud platforms is highly valued.

Qualifications

• Proficient in Python and AI-first quality engineering concepts.
• Experience with LLMs, prompting and agentic AI frameworks.
• Understanding of RAG and vector databases.
• Ability to design autonomous test systems and data management.

Responsabilités

• Design and build AI agents for test scenario and test case generation.
• Develop multi-agent systems for end-to-end testing: test authoring, execution, maintenance.
• Collaborate with Product, Dev, and QA teams to drive AI-first QE.

Connaissances

Python

LLMs & Prompting

Test automation

Autonomous testing

API integration

SQL/NoSQL basics

Cloud platforms

Outils

LangChain

LangGraph

CrewAI

AutoGen

Semantic Kernel

Description du poste

Be yourself – Charlie makes interviews comfortable and conversational

Interview Process

1. Quick video chat with Charlie, our AI interviewer
2. Verify your identity, Email and mobile verification
3. Mic and camera check
4. Chat with Charlie, Brief conversation about the role, We'll be in touch soon

This is an AI‑powered experience; despite best efforts, responses may at times be unexpected or inaccurate.

Skills & Keywords

Required Skills

Python LLMs LangChain RAG SQL

Good to have

QA Synthetic data ML basics

Job Description

Role & responsibilities

Role: SDET – AI First Quality Engineer

Experience: 3–6 Years

Role Overview

We are looking for an SDET – AI-First Quality Engineer with strong expertise in

building autonomous testing systems using Agentic AI.

Unlike traditional automation roles, this position focuses on creating intelligent AI agents that can:

• Understand requirements
• Execute and adapt tests autonomously
• Create and manage test data dynamically

The ideal candidate will help us move from regular Automation frameworks → Autonomous AI-driven Quality Engineering systems.

This is a high-impact role focused on building next-generation QE capabilities powered by LLMs, agents, and intelligent orchestration systems.

Key Responsibilities:

• Design and build AI agents for test scenario and test case generation
• Develop agents that convert:
• Create multi-agent systems for end-to-end testing, including:
  • Test Authoring
  • Test Execution
  • Test Maintenance
• Collaborate with Product, Dev, and QA teams to drive AI-first QE

Required Skills

• Strong programming skills in Python (mandatory)
• Experience working with LLMs (Large Language Models) and Prompt
• Hands-on experience with any of the Agentic AI frameworks:
  • LangChain / LangGraph
  • CrewAI / AutoGen / Semantic Kernel
• Understanding of RAG (Retrieval-Augmented Generation) and vector databases
• Experience in building AI workflows or pipelines (multi-step reasoning, tool usage, orchestration).
• Ability to integrate APIs, databases, and external tools within AI systems.
• Basic knowledge of SQL/NoSQL databases.
• Exposure to cloud platforms (AWS / Azure / GCP) for deploying AI solutions.
• Experience in building end-to-end AI/LLM-based applications is highly preferred.

Nice to Have

• Exposure to testing concepts (QA/QE mindset)