{"id":3462830,"url":"https://alion.io/job/cshark-senior-data-engineer-speech-data-sourcing","title":"Senior Data Engineer – Speech Data Sourcing","company":{"id":1383,"name":"CSHARK","domain":"cshark.com","url":"https://alion.io/company/cshark","size_band":null,"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":"senior","employment_type":"contractor","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["Wrocław, Poland","Warsaw, Poland","Gdańsk, Poland","Kraków, Poland"],"countries":["PL"],"hiring_countries":["PL"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":67000,"max_usd":101000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":71},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"GDPR","optional":false},{"name":"Python","optional":false}],"status":"live","first_seen_at":"2026-10-29T13:14:12Z","employer_posted_date":null,"last_verified_at":"2026-10-29T13:14:12Z","board_verified":false,"closed_at":null,"days_open":3,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":3},"description":"About the project \nYou will join a CSHARK team delivering a project for our client, a technology company building on-device audio and speech products. \nYou will own how the client acquires speech data for training its models. You will manage vendors and recording campaigns end to end, and make sure every dataset arrives on time, on budget, at the agreed quality and with proper legal grounds. \n\nIN SHORT:\n🌎 100% remote or from the office (Wrocław, Bielsko-Biała) - You choose!\n💰 120 - 190 PLN/h\n☑️ B2B contract\n\nYour responsibilities \nManage speech data vendors, from sourcing and scoping to delivery. \n\nDefine recording protocols, acceptance criteria and quality control for deliveries. \n\nPlan and track data acquisition budgets. \n\nBuild Python pipelines for audio and metadata processing and validation. \n\nVersion datasets and keep their lineage clear. \n\nEnsure consent, licensing and GDPR compliance for biometric data. \n\nWhat we expect \nExperience in data engineering, preferably with audio or speech data. \n\nStrong Python. \n\nDataset versioning tools (e.g. DVC). \n\nExperience working with external data vendors or annotation/recording providers. \n\nExperience with data quality control and acceptance processes. \n\nUnderstanding of GDPR, consent and data licensing (biometric data a plus). \n\nFluent English. \n\nNice to have \nKnowledge of speech recording practices and audio formats. \n\nExperience in ML/AI data operations. \n\nWhat we offer \nA fully remote role on a long-term project for an international client. \n\nWork on cutting-edge on-device audio technology used in real consumer devices. \n\nA team of experienced engineers and direct contact with the client’s R&D. \n\nStable cooperation with CSHARK, plus support from our delivery and people teams throughout the project. \n\nTech stack\nPython\nData Engineering","description_format":"text","description_chars":1814,"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":[{"name":"Poland","iso":"PL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Outsourcing & Dedicated Teams","Mobile App Development Services","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-29T14:25:00Z"}],"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":30,"reasons":["seen:3","velocity","win:early"],"computed_at":"2026-11-02T06:13:15Z"},"pay":null,"html_url":"https://alion.io/job/cshark-senior-data-engineer-speech-data-sourcing","json_url":"https://alion.io/job/cshark-senior-data-engineer-speech-data-sourcing.json","meta":{"generated_at":"2026-11-02T09:30:31Z","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":13296,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-03T00:00:00Z"}},"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":1383},"rest":"https://alion.io/mcp/rest/get_company?id=1383"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcshark-senior-data-engineer-speech-data-sourcing"},{"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%2Fcshark-senior-data-engineer-speech-data-sourcing"},{"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%2Fcshark-senior-data-engineer-speech-data-sourcing"},{"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/cshark-senior-data-engineer-speech-data-sourcing\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcshark-senior-data-engineer-speech-data-sourcing"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3462830}},{"tool":"search_jobs","arguments":{"company":"cshark.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3462830},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}