Python Automation Engineer Web Scraping & AI ( 2 - 4 Yrs )

About the job

Python Automation Engineer Web Scraping & AIExperience: 1 4 YearsLocation: Remote (WFH) / Bangalore / IndiaMode of Engagement: Full-timeNo of Positions: 3Industry: AI / SaaS / Automation / Data EngineeringNotice Period: Immediate Joiners Preferred

What We Are Looking For:

• 1 4 years of experience in Python-based web scraping, browser automation, and large-scale data extraction projects.
• Strong hands-on experience with Playwright, Selenium, Scrapy, Requests, BeautifulSoup, or similar scraping frameworks.
• Experience scraping dynamic JavaScript-heavy websites and handling complex DOM structures, login sessions, cookies, proxies, CAPTCHA, and anti-bot protections.
• Hands-on experience using LLMs and AI tools such as OpenAI APIs, ChatGPT, Claude, Gemini, LangChain, or AI agents for automating unstructured web data extraction and processing workflows.
• Experience building AI-assisted scraping pipelines for extracting, cleaning, structuring, validating, and enriching unstructured web content.
• Good understanding of browser automation, headless browsers, web crawling, and scalable scraping architectures.
• Experience working with APIs, JSON/XML handling, databases, automation workflows, and Python scripting.
• Familiarity with Docker, Linux, Git, cloud platforms, and workflow orchestration tools is an added advantage.
• Strong debugging, analytical, and problem-solving skills with the ability to work in fast-paced AI product environments.

Responsibilities

• Develop and maintain scalable web scraping and browser automation systems for structured and unstructured web data extraction.
• Build advanced scraping workflows using Playwright, Selenium, Scrapy, APIs, and Python automation frameworks.
• Handle dynamic JavaScript-based websites, browser rendering challenges, anti-bot protections, proxies, and session management.
• Build AI-powered extraction and automation workflows using LLMs, AI agents, and modern AI automation frameworks.
• Work on unstructured content extraction, intelligent parsing, classification, summarization, and data enrichment workflows using AI models.
• Optimize crawler performance, improve scraping reliability, and maintain high-quality data pipelines.
• Collaborate with AI, engineering, and product teams for scalable data acquisition and automation projects.
• Monitor scraping jobs, debug failures, and improve automation efficiency across large-scale scraping systems.