{"id":2501185,"url":"https://alion.io/job/gobblecube-data-acquisition-engineer","title":"Data Acquisition Engineer","company":{"id":46465,"name":"Gobblecube","domain":"gobblecube.ai","url":"https://alion.io/company/gobblecube","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Gurgaon, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":17500,"max_usd":48000,"period":"year","method":"role_country_seniority_unknown","sample_n":141},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Akamai","optional":false},{"name":"Apache Kafka","optional":false},{"name":"Celery","optional":false},{"name":"Cloudflare","optional":false},{"name":"Python","optional":false},{"name":"Redis","optional":false},{"name":"Scrapy","optional":false},{"name":"WebSockets","optional":false},{"name":"AWS","optional":true},{"name":"Burp Suite","optional":true},{"name":"Charles Proxy","optional":true},{"name":"Docker","optional":true},{"name":"Frida","optional":true},{"name":"GCP","optional":true},{"name":"Kubernetes","optional":true},{"name":"Playwright","optional":true},{"name":"RabbitMQ","optional":true},{"name":"Selenium","optional":true}],"status":"live","first_seen_at":"2026-10-14T05:57:48Z","employer_posted_date":null,"last_verified_at":"2026-10-14T05:57:48Z","board_verified":false,"closed_at":null,"days_open":2,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":2},"description":"The role involves building and scaling automated web crawlers and data extraction systems using Python and Scrapy. You'll also be working on anti-bot and WAF challenges, optimising proxies and crawler configurations, and building distributed systems using tools like Redis, Kafka, and Celery. Additionally, you will work on mobile API analysis, including understanding how iOS and Android applications communicate with backend systems and extracting data through APIs.\nResponsibilities:\nScale and Architecture: Architect, build, and optimise high-throughput crawler networks using Python and the Scrapy framework.\nAnti-Bot and WAF Defence: Develop robust, automated mechanisms to bypass advanced anti-bot protections, rate limits, enterprise WAFs (e. g., Akamai Bot Manager, Cloudflare, Datadome), and complex CAPTCHA challenges.\nInfrastructure Optimisation: Implement proxy rotation, custom Scrapy middleware, request fingerprinting, header emulation, and TLS/JA3 fingerprint spoofing.\nDistributed Orchestration: Build distributed queuing and scraping architectures using Scrapy, Redis, Kafka, and Celery for seamless execution at scale.\nMobile Reverse Engineering: Analyse mobile network traffic (iOS/Android), inspect API endpoints, perform certificate unpinning, and extract data directly from native mobile backend APIs.\nRequirements:\nScrapy Mastery: Deep internal knowledge of Scrapy (Twisted engine, asynchronous networking, custom pipelines, spider middleware, and extensions).\nAnti-Bot Infra Expertise: Proven track record bypassing enterprise anti-scraping systems (Akamai Bot Detection, Cloudflare, Imperva, Datadome, PerimeterX).\nNetwork and Protocol Mastery: Deep understanding of HTTP/HTTPS, HTTP/2, WebSocket protocols, TLS signatures/fingerprinting (JA3/JA4), request headers, and cookie management.\nScale Experience: Direct experience running distributed crawling infrastructure handling millions of requests daily.\nPreferred Qualifications:\nMobile Application Reverse Engineering: Experience with tools like Frida, Charles Proxy, Mitmproxy, or Burp Suite to intercept, analyse, and bypass mobile SSL pinners.\nDevice Farm Management: Hands-on experience working with mobile device farms (Real device or Emulated Android/iOS farms) for app automation.\nBrowser Automation and Bypassing: Experience integrating Scrapy with undetected headless engines (Playwright, Selenium-Stealth, Puppeteer-Extra).\nData Pipelines and Cloud Infrastructure: Familiarity with AWS/GCP, Docker, Kubernetes, and streaming message queues (Kafka, Redis, RabbitMQ).","description_format":"text","description_chars":2555,"description_truncated":false,"requirements":{"experience_years_min":null,"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":["Marketing Automation","Customer Data Platforms (CDP) & Reverse ETL"],"lifecycle":[{"event":"open","at":"2026-10-14T05:57:48Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":1,"expected_fill_days":33,"reasons":["seen:1","win:early"],"computed_at":"2026-10-16T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/gobblecube-data-acquisition-engineer","json_url":"https://alion.io/job/gobblecube-data-acquisition-engineer.json","meta":{"generated_at":"2026-10-16T08:41:29Z","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":6639,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-17T00:00:00Z"}},"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":46465},"rest":"https://alion.io/mcp/rest/get_company?id=46465"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fgobblecube-data-acquisition-engineer"},{"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%2Fgobblecube-data-acquisition-engineer"},{"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%2Fgobblecube-data-acquisition-engineer"},{"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/gobblecube-data-acquisition-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fgobblecube-data-acquisition-engineer"}]}