Job Description

Position Objective\nDevelop, optimize and maintain web scraping solutions, data automation and tools based on artificial intelligence for the extraction, cleaning, classification and structuring of information from various sources. Ensure that processes are efficient, scalable, accurate and aligned by facilitating decision making through reliable data.\nResponsibilities\nDevelop Web Scraping bots using Scrapy, Selenium, Playwright or BeautifulSoup.\nImplement anti-blocking strategies, proxy rotation and captcha management.\nIntegrate AI models (OpenAI, Gemini, AWS Bedrock, etc.) for:\nCleaning and data classification\nAutomatic summaries\nEnrichment and intelligent structuring\nDesign ETL pipelines and process automation.\nIntegrate with external APIs (REST / GraphQL).\nOptimize processes to improve speed, reliability and scalability.\nDocument processes and generate technical reports.\nRequirements\nBachelor's degree in Systems, Computer Science, Computing or similar.\n3+ years of experience in Web Scraping advanced.\nProficiency in Python and frameworks Scrapy, Selenium, Playwright.\nExperience with AI models (LLMs, embeddings, classification).\nManagement of SQL, NoSQL, JSON, Regex.\nExperience in automation, data processing and APIs.\nKnowledge of Git and agile methodologies.\nSkills\nAnalysis and problem resolution\nLogical thinking\nAttention to detail\nFast learning\nTechnical communication\nWe offer\nCompetitive salary according to experience\nHybrid scheme\nDevelopment opportunity in projects with AI\nCorporate and professional environment",