{"id":3101746,"url":"https://alion.io/job/apeiro-data-scientist","title":"Data Scientist","company":{"id":3313,"name":"Apeiro","domain":"apeiro.digital","url":"https://alion.io/company/apeiro","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":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Noida, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":19000,"max_usd":39000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":71},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"NLP","optional":false},{"name":"RAG","optional":false},{"name":"SQL","optional":false},{"name":"ClickHouse","optional":true},{"name":"dbt","optional":true},{"name":"FHIR","optional":true},{"name":"Google BigQuery","optional":true},{"name":"LangChain","optional":true},{"name":"LlamaIndex","optional":true},{"name":"NumPy","optional":true},{"name":"Pandas","optional":true},{"name":"Python","optional":true},{"name":"Scikit-learn","optional":true},{"name":"Snowflake","optional":true},{"name":"Time Series","optional":true}],"status":"live","first_seen_at":"2026-10-22T17:35:00Z","employer_posted_date":null,"last_verified_at":"2026-10-22T17:35:00Z","board_verified":false,"closed_at":null,"days_open":2,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":2},"description":"Responsibilities: \nEnd-to-End Ownership: The role expects candidates to take ambiguous business/clinical questions, scope them into data problems, build models, and deliver measurable outcomes.\nCore Work: Predictive modeling in supply chain forecasting, claims/denial analytics, and population health indicators.\nAdvanced ML and AI: Strong emphasis on NLP, LLMs, and RAG systems, including text-to-SQL, retrieval over schemas, and grounding outputs to trusted data.\nProduction Focus: Models must be production-ized pipelines, with retraining, monitoring, and drift detection, not just research prototypes.\nCollaboration: Partnering with product, domain, and government stakeholders; clear communication of findings and limitations.\nLeadership: Setting analytical standards, mentoring junior scientists, and contributing to architecture/tooling decisions.\n\nRequirements: \nExperience: 5+ years in data science with shipped models.\nTech Stack: Python (Pandas, NumPy, scikit-learn, and deep learning frameworks), SQL, and columnar DBs (ClickHouse, BigQuery, and Snowflake).\nSpecialized Skills: NLP, LLMs, RAG, text-to-SQL, MLOps.\nNice-to-Have: Health data (FHIR, claims, logistics), time-series forecasting, causal inference, LangChain/LlamaIndex, dbt, and lakehouse architectures.\nSkills\nLLM, NLP, Python, RAG, SQL, large language model, natural language processing, retrieval augmented generation","description_format":"text","description_chars":1394,"description_truncated":false,"requirements":{"experience_years_min":5,"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":["Custom Software Development","Primary Care & Medical Centers"],"lifecycle":[{"event":"open","at":"2026-10-22T17:35:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":2,"expected_fill_days":27,"reasons":["seen:2","velocity","win:early"],"computed_at":"2026-10-25T05:49:26Z"},"pay":null,"html_url":"https://alion.io/job/apeiro-data-scientist","json_url":"https://alion.io/job/apeiro-data-scientist.json","meta":{"generated_at":"2026-10-25T06:59:14Z","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":9842,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-26T00:00:00Z"}},"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":3313},"rest":"https://alion.io/mcp/rest/get_company?id=3313"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fapeiro-data-scientist"},{"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%2Fapeiro-data-scientist"},{"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%2Fapeiro-data-scientist"},{"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/apeiro-data-scientist\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapeiro-data-scientist"}]}