{"id":142763,"url":"https://alion.io/job/veryfi-data-annotation-engineer","title":"Data Annotation Engineer","company":{"id":7750,"name":"Veryfi","domain":"veryfi.com","url":"https://alion.io/company/veryfi","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Work at a Startup","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Medellín, Colombia"],"countries":[],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":35000,"max":40000,"currency":"USD","period":"year","gross":null,"usd_annual":40000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Machine Learning","optional":false},{"name":"NumPy","optional":false},{"name":"Pandas","optional":false},{"name":"Python","optional":false},{"name":"SciPy","optional":false},{"name":"Linux","optional":true},{"name":"NLP","optional":true}],"status":"live","first_seen_at":"2026-08-28T01:35:10Z","employer_posted_date":"2026-10-13","last_verified_at":"2026-10-18T02:17:26Z","board_verified":true,"closed_at":null,"days_open":51,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":51},"description":"Veryfi is a YC-funded Silicon Valley startup that uses AI to understand documents like receipts and invoices. As a Data Engineer at Veryfi, you'll contribute to the evolution of our training data infrastructure and the development of new features and projects. You'll gather, process, and analyze diverse datasets to generate high-quality training data for our machine-learning models. Furthermore, by delving deep into our system, you'll have the autonomy to identify challenges and opportunities, taking ownership of developing solutions to refine existing tools and algorithms.\nKey Responsibilities:\nGather, process, and analyze diverse datasets to generate training data that fuels the development of our ML projects.\nExpand and optimize the training data pipelines to improve the speed and accuracy of our processes.\nCollaborate with a cross-functional team to define requirements and prioritize development efforts.\nEssential Skills:\nProficient in Python programming for data handling and processing, with experience in utilizing data science tools such as Pandas, NumPy, SciPy, and others.\nStrong analytical thinking with a focus on delivering results.\nMeticulous attention to detail, ensuring accuracy and precision in all data handling and processing tasks.\nEnthusiastic about learning and adapting to new technologies and methodologies, particularly in the realm of Machine Learning (ML).\nInnovation mindset, adept at challenging existing processes and driving positive change.\nPreferred Qualifications:\nFamiliarity with regex development, software engineering principles, and Linux command line tools.\nExperience with Natural Language Processing (NLP) techniques and libraries, including the use of Large - - -- - Language Models (LLMs) and supervised learning for document data extraction.\nEffective organizational abilities, capable of managing projects independently from inception to completion.\nExceptional verbal and written communication skills, effectively communicating problems, proposed solutions, and results to stakeholders in a multicultural environment.\nA Bachelor's degree in computer science, engineering, or a related field. Postgraduate studies are a plus but not required.\nKeywords: NLP, Patterns Detection, Data Labeling, Software Development, Data Engineering.","description_format":"text","description_chars":2293,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Colombia","iso":null,"kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Computer Vision","Document AI","Accounting & Tax Software"],"lifecycle":[{"event":"open","at":"2026-08-28T01:35:10Z"}],"visa":[],"liveness":{"score":27,"band":"fade","label":"Fading","p_open":1,"p_active":0.49,"p_room":0.55,"age_days":50,"expected_fill_days":38,"reasons":["conf:2","win:tail"],"computed_at":"2026-10-17T05:46:00Z"},"pay":{"stated_usd_annual":40000,"is_top_pay":false},"html_url":"https://alion.io/job/veryfi-data-annotation-engineer","json_url":"https://alion.io/job/veryfi-data-annotation-engineer.json","meta":{"generated_at":"2026-10-18T04:25:22Z","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":6581,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-19T00:00:00Z"}},"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":7750},"rest":"https://alion.io/mcp/rest/get_company?id=7750"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fveryfi-data-annotation-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%2Fveryfi-data-annotation-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%2Fveryfi-data-annotation-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/veryfi-data-annotation-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fveryfi-data-annotation-engineer"}]}