{"id":3176860,"url":"https://alion.io/job/osi-digital-data-engineer-web-scrapingcrawling","title":"Data Engineer (Web Scraping/Crawling)","company":{"id":3800690,"name":"OSI Digital","domain":"osidigital.com","url":"https://alion.io/company/osi-digital","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"JazzHR","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Hyderabad, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":13500,"max_usd":35000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":21},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Beautiful Soup","optional":false},{"name":"Python","optional":false},{"name":"Scrapy","optional":false},{"name":"Selenium","optional":false},{"name":"SQL","optional":false},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"ETL/ELT","optional":true},{"name":"GCP","optional":true}],"status":"live","first_seen_at":"2026-10-23T17:24:52Z","employer_posted_date":null,"last_verified_at":"2026-10-23T17:24:52Z","board_verified":false,"closed_at":null,"days_open":3,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":3},"description":"Job Title: Web Crawling Engineer\n\nExperience:3-5 Years\n\nLocation: Hyderabad\n\nWe are looking for a skilled Web Crawling Engineer with strong expertise in Python and hands-on experience building scalable crawlers and scrapers. The ideal candidate should have deep knowledge of crawling frameworks, anti-blocking techniques, and proxy management, along with experience solving challenges like captchas and rate-limiting.\n\nKey Responsibilities\n\nDesign, develop, and maintain scalable and efficient web crawlers for data extraction.\nWork with Scrapy, Requests, and other Python libraries to implement crawling solutions.\nHandle anti-scraping measures, including IP blocks, rate limits, and captchas.\nImplement and manage proxy rotation and session management strategies.\nEnsure high-quality and structured data extraction, cleaning, and storage.\nMonitor crawler performance, troubleshoot issues, and optimize for reliability and efficiency.\nCollaborate with the data engineering team to integrate crawled data into pipelines.\nStay updated with the latest tools, techniques, and best practices in web crawling.\n\nRequired Skills & Qualifications\n\nStrong programming skills in Python.\nProven experience with Scrapy, Requests, BeautifulSoup, Selenium (if required).\nHands-on experience solving blocking issues, handling\nGood understanding of proxy usage, rotation, and fingerprinting avoidance techniques.\nKnowledge of HTTP, cookies, headers, sessions, and request/response cycles.\nExperience with databases (SQL/NoSQL) for storing crawled data.\nStrong debugging, problem-solving, and analytical skills.\n\nGood to Have\n\nExperience with cloud environments (AWS, GCP, Azure).\nKnowledge of data pipelines and ETL processes.\n\nEducation & Experience\n\nBachelor's degree in Computer Science, Information Technology, or equivalent practical experience.\n3+ years of experience in web crawling or related fields","description_format":"text","description_chars":1891,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Consulting & Digital Transformation","Enterprise Apps Implementation Partners","Analytics & BI Consulting"],"lifecycle":[{"event":"open","at":"2026-10-23T20:09:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":3,"expected_fill_days":17,"reasons":["seen:3","velocity","win:early"],"computed_at":"2026-10-27T05:46:45Z"},"pay":null,"html_url":"https://alion.io/job/osi-digital-data-engineer-web-scrapingcrawling","json_url":"https://alion.io/job/osi-digital-data-engineer-web-scrapingcrawling.json","meta":{"generated_at":"2026-10-27T10:53:02Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":12771,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-28T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":3800690},"rest":"https://alion.io/mcp/rest/get_company?id=3800690"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fosi-digital-data-engineer-web-scrapingcrawling"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fosi-digital-data-engineer-web-scrapingcrawling"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fosi-digital-data-engineer-web-scrapingcrawling"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/osi-digital-data-engineer-web-scrapingcrawling\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fosi-digital-data-engineer-web-scrapingcrawling"}]}