{"id":1994914,"url":"https://alion.io/job/saic-data-scientist-5","title":"Data Scientist","company":{"id":58788,"name":"SAIC","domain":"saic.com","url":"https://alion.io/company/saic","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Oracle","truth_index":{"grade":"B","score":80,"open_postings":48,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":12,"computed_at":"2026-10-09T06:01:00Z"}},"role":"Data Science","role_family":"Data Science","seniority":"staff","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["McLean, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":133000,"max_usd":265000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":334},"experience_years_min":9,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Encoder-Decoder","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Gensim","optional":false},{"name":"GitHub","optional":false},{"name":"Hugging Face","optional":false},{"name":"Jenkins","optional":false},{"name":"Keras","optional":false},{"name":"Machine Learning","optional":false},{"name":"NLP","optional":false},{"name":"NLTK","optional":false},{"name":"Oracle","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Scikit-learn","optional":false},{"name":"SQL","optional":false},{"name":"TensorFlow","optional":false},{"name":"Transformers","optional":false},{"name":"Flask","optional":true},{"name":"Semantic Search","optional":true},{"name":"Tableau","optional":true}],"status":"live","first_seen_at":"2026-07-09T16:06:55Z","employer_posted_date":"2026-07-09","last_verified_at":"2026-10-09T23:32:00Z","board_verified":true,"closed_at":null,"days_open":92,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":92},"description":"SAIC is seeking a Data Scientist to join our team to provide Subject Matter expertise and support specializing in natural language(NLP) processing and associated data preparation. The ideal candidate will have experienced SQL and Python skills to transform both structured and unstructured data into clear and concise analytic insights. This position in in Mclean, VA and requires a TS/SCI with polygraph.\nKey Responsibilities:\nWork closely with data scientist and technical team to implement requirements.\nConduct sophisticated analysis using deployed tools and natural language processing (NLP).\nAnalyze large amounts of raw data, including text data, to provide business insights.\nPreprocess or clean structured and unstructured data, including text data.\nDesign and implement advanced ETL code and table configurations for complex data sets. \nUse Structured Query Language (SQL) in Sponsor’s Oracle database to develop and organize relevant information with supporting analytics. \nAuthor analytic publications and produce ad-hoc reports to include data visualization.\nStay current with enterprise metadata collection tools.\nProvide technical education to staff on an ad-hoc basis. \nProvide subject matter expertise in natural language processing (NLP).\n Bachelors and fourteen (14) years or more experience; Masters and twelve (12) years or more experience; PhD or JD and nine (9) years or more experience.\nDemonstrated professional or academic experience performing NLP tasks, including selecting the best Python libraries for a given task, choosing appropriate pre-processing actions, performing analysis, and assessing model performance.\nDemonstrated professional or academic experience using Python NLP packages such as Spacy, Gensim, or NLTK to analyze or process collections of documents.\nDemonstrated professional or academic experience with deep learning frameworks such as PyTorch, Tensorflow, or Keras.\nDemonstrated professional or academic experience with the HuggingFace Transformers library and hub.\nDemonstrated experience creating machine learning models that conduct text classification and topic modeling in Python using standard machine learning (Scikit-learn) or deep learning models.\nDemonstrated academic or professional experience using encoder-decoder and generative language models to perform NLP tasks.\nDemonstrated academic or professional experience communicating methodological choices and model results.\nDemonstrated professional or academic experience and proficiency with SQL to include using common table expressions, set operations, aggregated functions and nested subqueries.\nDemonstrated professional or academic experience with version control systems such as Github and Jenkins.\nDemonstrated experience leveraging GPUs for accelerated computing.\nDeveloped practical approaches for measuring performance.\nAssisted in developing types of measure, the collection of data, analyzing the data, and presenting that data to senior leadership.\nConducted advanced statistical analysis on personnel, intelligence, and performance metrics.\nAssisted in selection or development of appropriate methodology to conduct research.\nAnalyzed information and provide research findings in a manner that is easily grasped by the customer and consumers.\nTS/SCI with polygraph.\nDesired Skills:\nExperience writing Python scripts that pull data from web-based APIs and relational databases.\nExperience with cloud computing development and architecture.\nDemonstrated experience with front-end web development frameworks such as Flask.\nDemonstrated experience developing applications for semantic search.\nDemonstrated experience tuning LLMs on custom data sets and applying results to specific use cases.\nDemonstrated professional or academic experience and proficiency with Tableau to produce visualizations and dashboards.","description_format":"text","description_chars":3837,"description_truncated":false,"requirements":{"experience_years_min":9,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":true,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Digital Government","Systems Integrators","Engineering Services"],"lifecycle":[{"event":"open","at":"2026-10-07T08:30:53Z"}],"visa":[],"liveness":{"score":6,"band":"cold","label":"Long shot","p_open":1,"p_active":0.214,"p_room":0.28,"age_days":91,"expected_fill_days":12,"reasons":["conf:2","stale_co","evergreen","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-09T06:01:00Z"},"pay":null,"html_url":"https://alion.io/job/saic-data-scientist-5","json_url":"https://alion.io/job/saic-data-scientist-5.json","meta":{"generated_at":"2026-10-10T01:08:29Z","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":1938,"day_limit":5000,"remaining_today":3062,"minute_limit":60,"resets_at":"2026-10-11T00:00:00Z"}},"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":58788},"rest":"https://alion.io/mcp/rest/get_company?id=58788"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsaic-data-scientist-5"},{"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%2Fsaic-data-scientist-5"},{"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%2Fsaic-data-scientist-5"},{"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/saic-data-scientist-5\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsaic-data-scientist-5"}]}