{"id":1648055,"url":"https://alion.io/job/institute-of-foundation-models-data-engineer","title":"Data Engineer","company":{"id":99421,"name":"Institute of Foundation Models","domain":"ifm.ai","url":"https://alion.io/company/institute-of-foundation-models","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":{"grade":"A","score":95,"open_postings":41,"ghost_share":0,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":482,"computed_at":"2026-11-02T06:13:15Z"}},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Sunnyvale, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":150000,"max":450000,"currency":"USD","period":"year","gross":null,"usd_annual":450000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache Kafka","optional":false},{"name":"AWS","optional":false},{"name":"GitHub","optional":false},{"name":"Kubernetes","optional":false},{"name":"LLM","optional":false},{"name":"NLP","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2025-04-09T18:10:06Z","employer_posted_date":"2025-04-09","last_verified_at":"2026-11-03T01:49:01Z","board_verified":true,"closed_at":null,"days_open":572,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":571},"description":"The Role\nAs a Data Engineer specializing in Natural Language Processing (NLP) and large-scale data processing, you will quickly and effectively gather, curate, and prepare high-quality datasets to support cutting-edge NLP research. Your role will be instrumental in enabling researchers by delivering essential data through efficient and scalable engineering practices, including web crawling, LLM-generated content refinement, and robust data pipelines, primarily leveraging Python and related technologies.\nKey Responsibilities\nRapidly collect, curate, and preprocess datasets based on detailed specifications provided by NLPresearchers,delivering data within tight timelines.\nDevelop and maintain efficient web crawling solutions, APIs, and automated workflows to continuously improve data collection processes.\nRefine and evaluate outputs from Large Language Models (LLMs) to generate structured datasets suitable for model training and benchmarking.\nImplement scalable data pipelines, ensuring efficient data processing, storage, retrieval, and distribution to research teams.\nCollaborate closely with researchers and engineers to ensure collected data meets specified quality and relevance criteria.\nDocument data collection methodologies, dataset characteristics, and pipeline architecture clearly and effectively.\nEngage with peer teams and participate in technical reviews to uphold best practices and data quality standards.\nRepresent MBZUAI at industry and research forums, showcasing technical capabilities in large-scale data processing and AI data infrastructure.\nAcademic Qualifications\nBachelor's degree in Computer Science, Data Science, Engineering, or a related technical field required\nMaster’s degree or PhD degree or equivalent experience in Computer Science, Data Engineering, or related technical fields preferred.\nProfessional Experience - Required\nExtensive experience in data engineering, data processing, and automation using Python.\nDemonstrated proficiency in designing and deploying web crawling solutions, automated data extraction, and processing pipelines.\nStrong understanding of data structures, algorithms, databases, SQL, and performance optimization.\nExperience working with cloud infrastructure and distributed data processing frameworks (e.g., AWS, Spark, Kafka, Kubernetes).\nExcellent problem-solving abilities, attention to detail, and the capability to rapidly address technical challenges.\nStrong communication and collaboration skills with cross-functional teams.\nProfessional Experience - Preferred\nProven track record of supporting NLP or AI research teams with rapid and reliable data delivery.\nExperience working with large language models, including evaluation, efficient inference, and prompt engineering.\nExperience with refining outputs from large-scale AI models, such as LLM-generated data.\nContributions to open-source projects, coding competitions, or high visibility in coding communities (e.g., GitHub, Stack Overflow).\nFamiliarity with the latest advancements in NLP data processing and large language model technologies.","description_format":"text","description_chars":3082,"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":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Foundation Models","AI Research Labs"],"lifecycle":[{"event":"open","at":"2026-10-02T00:08:08Z"}],"visa":[],"liveness":{"score":32,"band":"fade","label":"Fading","p_open":1,"p_active":0.732,"p_room":0.44,"age_days":571,"expected_fill_days":482,"reasons":["conf:2","velocity","win:tail","crowd:"],"computed_at":"2026-11-02T06:13:15Z"},"pay":{"stated_usd_annual":450000,"is_top_pay":true},"html_url":"https://alion.io/job/institute-of-foundation-models-data-engineer","json_url":"https://alion.io/job/institute-of-foundation-models-data-engineer.json","meta":{"generated_at":"2026-11-03T03:47:58Z","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":5124,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-04T00:00:00Z"}},"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":99421},"rest":"https://alion.io/mcp/rest/get_company?id=99421"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Finstitute-of-foundation-models-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%2Finstitute-of-foundation-models-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%2Finstitute-of-foundation-models-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/institute-of-foundation-models-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Finstitute-of-foundation-models-data-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":1648055}},{"tool":"search_jobs","arguments":{"company":"ifm.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":1648055},"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"}}