Artificial Intelligence Engineer

Purview Services; Ghaziabad District; Hybrid; INR 1,200,000 - 2,400,000; Full time

Job summary

Purview Services seeks an AI engineer specialized in testing to evaluate frontier agentic models and tooling. You will script tests in Python/TypeScript/JavaScript, orchestrate agent interactions, and validate API/database integrations within a hybrid work setup in Pune.

Experience of 5+ years in AI testing, prompt engineering, and DevOps practices is required. Familiarity with Playwright, JMeter, Selenium, LangChain, and CrewAI is a strong plus.

Qualifications

• Total Work experience ~5-10 years.
• Frontier agentic models: knowledge of Frontier agentic models (OpenAI GPT, Google Gemini AI, Anthropic Claude etc.) and building Agentic AI agents.
• MCP with Testing agents Selenium, Appium, Playwright, JMeter, Roboframework, commercial tools like TOSCA, TDM, DevTest.
• Prompt Engineering & Evaluation: Prompting to solve a QA problem, testing how agents respond to various instructions, chain-of-thought prompts, and few-shot techniques.
• Programming: Proficiency in Python, TypeScript, JavaScript for scripting, analyzing agent traces, and customizing test environments.
• System Architecture & Tooling: Test AI interactions with external tools, APIs, databases, and web services.
• DevOps expertise (SCM, Jenkins, Ansible).
• Testing Expertise: Proficiency in testing tools and scripting for automating test cases and validating agents functionality.

Skills

Python

TypeScript

JavaScript

Agentic AI

Prompt Engineering

Rapid Prototyping

DevOps

Testing

Tools

Selenium

Appium

Playwright

JMeter

Roboframework

TOSCA

TDM

DevTest

Insomnia

Karate

REST Assured

LangChain

CrewAI

Job description

Job title: Testing- AI engineer

Location: Pune, HYD

Experience: 5+ Years

Work Mode: Hybrid

Job Description:

JD for AI Engineers:

• Total Work experience ~5-10 years
• Frontier agentic models: Knowledge of Frontier agentic models (OpenAI GPT, Google Gemini AI, Anthropic Claude etc.,) and building Agentic AI agents.
• MCP with Testing agents Selenium, Appium, Playwright, JMeter, Roboframework, commercial tools like TOSCA, TDM, DevTest
• Prompt Engineering & Evaluation: Prompting to solve a QA problem, Testing how agents respond to various instructions, chain-of-thought prompts, and few-shot techniques.
• Programming: Proficiency in Python, TypeScript, JavaScript is required for scripting, analyzing agent traces, and customizing test environments. Rapid prototyping
• System Architecture & Tooling: Ability to test AI interactions with external tools, APIs, databases, and web services (e.g., verifying tool selection and API payload accuracy).
• DevOps expertise (SCM, Jenkins, Ansible)
• Testing Expertise (Good to have):
• Proficiency in testing tools, Agentic Testing Playwright, Performance Testing- Apache JMeter, API Testing tools Insomnia, Karate, REST Assured.
• Writing scripts to automate test cases, debug, and monitor agent actions.
• Validating agents functional and technical features, integration with external tools, APIs, and databases (e.g., LangChain, CrewAI).