{"id":1632498,"url":"https://alion.io/job/vtg-data-scientist","title":"Data Scientist","company":{"id":2946912,"name":"VTG","domain":"vtg.com","url":"https://alion.io/company/vtg-com","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":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Beavercreek, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":103000,"max_usd":222000,"period":"year","method":"role_country_seniority_unknown","sample_n":2605},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon S3","optional":false},{"name":"Amazon SageMaker","optional":false},{"name":"Apache Kafka","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"GCP","optional":false},{"name":"Git","optional":false},{"name":"GitLab","optional":false},{"name":"HBase","optional":false},{"name":"Java","optional":false},{"name":"Jenkins","optional":false},{"name":"JFrog Artifactory","optional":false},{"name":"Keras","optional":false},{"name":"Linux","optional":false},{"name":"Machine Learning","optional":false},{"name":"MATLAB","optional":false},{"name":"NumPy","optional":false},{"name":"Python","optional":false},{"name":"Scikit-learn","optional":false},{"name":"Seaborn","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"TensorFlow","optional":false},{"name":"Matplotlib","optional":true}],"status":"closed","first_seen_at":"2026-09-03T02:10:21Z","employer_posted_date":null,"last_verified_at":"2026-10-10T16:54:15Z","board_verified":false,"closed_at":"2026-10-10T16:54:15Z","days_open":37,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":37},"description":"Overview\n\nVTG is seeking a Data Scientist to support our Team in Beavercreek, OH. The Data Scientist will design, prototype, and implement a data management and application development pipeline in support of national defense data science and data architecture prototyping tasks. This role will also include gathering and organizing data, conducting data analytics, and developing data analytic and AI/ML based applications. This is an onsite role due to its classification level. \n\nWhat will you do?\n\nThe Data Scientist will work with a team of DevOps engineers, software developers, data engineers, and system operators to identify data needs and prototype a range of novel solutions. This data scientist would be involved at all levels of the data life cycle from onboard management of data to its use in application development and back to application integration and gathering test data. \n Leverage third-party tools to architect and prototype a modern data management and application development pipeline in a local and/or a cloud environment \n Perform data analytics of simulated and real-world data \n Integrate structured and unstructured data from disparate data sources \n Develop applications and models supporting various users \n Provide technical input to program managers and government representatives \n\nDo you have what it takes?\n\nRequired qualifications: \n Bachelor's Degree, majoring in majoring in Computer Science, Data Science, Information Systems, or a related field \n 4+ years of experience as a Data Scientist including experience in statistical modeling and machine learning based on the analysis of large sets of data \n Experience with data storage and management tools (S3, SQL, MongoDB, Hbase, Apache Atlas, Kafka, etc.) \n Programming experience in Python, R, or similar data manipulation languages and associated libraries (e.g. pandas, numpy, polars, dask) \n Experience with data science and analytics toolsets (e.g. JupyterHub / Jupyter Notebooks, Apache Spark, MATLAB) \n Knowledge of data modeling principles \n Experience in knowledge extraction and insights from data in various forms, both structured and unstructured \n Cloud development experience, preferably in AWS \n Excellent verbal and written communication skills \n US Citizen with current TOP SECRET/SCI Eligible Clearance or ability to obtain a TOP SECRET/SCI clearance \n Successful completion of background check \n\n Desired qualifications: \n Master's Degree or higher in Computer Science, Data Science, or Information Systems \n Experience establishing data pipelines in cloud platforms, such as AWS, Azure, or Google Cloud \n Data visualization experience and associated tools/libraries (e.g. pyplot, seaborn) \n Experience using Git for version control and issue tracking \n Experience with artifact repositories (e.g. Artifactory) \n Experience with CI/CD pipelines (e.g. Jenkins, Gitlab pipelines) \n Experience with AI/ML development tools and libraries (e.g. Sagemaker, ML Studio, Tensorflow, Keras, scikit-learn) \n Experience leading teams and projects \n Programming experience in C++ and Java \n Experience with Linux systems","description_format":"text","description_chars":3117,"description_truncated":false,"requirements":{"experience_years_min":4,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":true,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-01T21:05:01Z"},{"event":"close","at":"2026-10-10T16:54:15Z"}],"visa":[],"liveness":null,"pay":null,"html_url":"https://alion.io/job/vtg-data-scientist","json_url":"https://alion.io/job/vtg-data-scientist.json","meta":{"generated_at":"2026-10-11T02:21:56Z","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","counted_by":"address","units_charged":1,"used_today":3785,"day_limit":5000,"remaining_today":1215,"minute_limit":60,"resets_at":"2026-10-12T00:00:00Z"}},"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":2946912},"rest":"https://alion.io/mcp/rest/get_company?id=2946912"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fvtg-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%2Fvtg-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%2Fvtg-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/vtg-data-scientist\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fvtg-data-scientist"}]}