{"id":1945153,"url":"https://alion.io/job/karya-data-engineer","title":"Data Engineer","company":{"id":63591,"name":"Karya","domain":"karya.in","url":"https://alion.io/company/karya","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"C","score":58,"open_postings":17,"ghost_share":0.706,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-16T05:45:00Z"}},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":null,"work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":18500,"max_usd":50000,"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":"Bash","optional":false},{"name":"ClickHouse","optional":false},{"name":"Linux","optional":false},{"name":"Node JS","optional":false},{"name":"Platform Engineering","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":false},{"name":"TypeScript","optional":false},{"name":"Amazon S3","optional":true},{"name":"Azure","optional":true},{"name":"GCP","optional":true},{"name":"JavaScript","optional":true},{"name":"Metabase","optional":true}],"status":"live","first_seen_at":"2026-10-06T05:05:38Z","employer_posted_date":"2026-10-06","last_verified_at":"2026-10-16T13:17:28Z","board_verified":true,"closed_at":null,"days_open":10,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":10},"description":"About Karya\n\nKarya provides AI-enabled earning and learning opportunities to economically underserved communities, and\nhigh-quality, ethically sourced datasets to research labs and technology companies. Digital workers earn at least 20\ntimes the local minimum wage. The platform has delivered over 40 million tasks.\nAbout the role\nThis role runs live client projects on the Karya platform. The work is the execution layer above the core product:\nproject workflows, data jobs, checks, reports, and delivery.\nYou will work with Operations and client teams on questions of progress, quality, pay, and files, and with platform\nengineers when a fix belongs in the product. Worker payouts and client deliverables depend on getting these checks\nright.\nResponsibilities\nRun and monitor data jobs on remote Linux servers, and recover failed jobs from logs and process state.\nConfigure project workflows, including the handoff from automated processing to human tasks, and track what\nis in progress, held, or ready to deliver.\nWrite PostgreSQL and ClickHouse queries for throughput, completion, quality, pay, and delivery status.\nApply completion and quality rules to access, pay, and delivery decisions, after a sample check.\nWrite Python, SQL, or Bash scripts for those checks and decisions, and keep them in the repository.\nPackage datasets to client specifications, move them through cloud object storage, and record what has shipped.\nRead the TypeScript / Node.js codebase to follow tasks, assignments, payments, and file storage.\nReply to Operations and client teams with the finding, the change made, and what is still open.\nReport repeated manual work to platform engineering, with an example.\nRequirements\nPostgreSQL, including joins, aggregates, and JSON fields.\nScripts in Python, Bash, or TypeScript, checked into git.\nAbility to read a TypeScript codebase and a relational schema.\nLinux for running jobs: SSH, logs, long-running processes, and disk.\nAbility to write technical updates that give non-technical teammates a clear picture of the situation.\nQueries or scripts already run against real project or production data.\nGood to have\nCloud object storage (Google Cloud Storage, S3, or Azure Blob).\nExperience with collected datasets such as speech, text, or images.\nClickHouse, Metabase, or a similar reporting tool.\nPerks\nFlexible leave, with remote or hybrid work.\nHealth insurance.\nDirect work on data collection that determines worker earnings and client deliverables.\nKarya is an equal opportunity employer. Applicants are considered without regard to race, religion, gender identity, sexual orientation,\ndisability, or any other protected status. For accommodations, contact .","description_format":"text","description_chars":2700,"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":["Health insurance","Hybrid work"],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["AI Training Data & Annotation"],"lifecycle":[{"event":"open","at":"2026-10-06T06:12:35Z"}],"visa":[],"liveness":{"score":48,"band":"ok","label":"Likely open","p_open":1,"p_active":0.535,"p_room":0.9,"age_days":10,"expected_fill_days":21,"reasons":["conf:1","stale_co","win:mid"],"computed_at":"2026-10-16T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/karya-data-engineer","json_url":"https://alion.io/job/karya-data-engineer.json","meta":{"generated_at":"2026-10-16T15:42:54Z","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":15574,"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":63591},"rest":"https://alion.io/mcp/rest/get_company?id=63591"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fkarya-data-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%2Fkarya-data-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%2Fkarya-data-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/karya-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fkarya-data-engineer"}]}