{"id":1621192,"url":"https://alion.io/job/exl-data-scientist-2","title":"Data Scientist","company":{"id":38016,"name":"EXL","domain":"exlservice.com","url":"https://alion.io/company/exl","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":62,"ghost_share":0,"stale_share":0.984,"repost_share":0,"time_to_fill_p50_days":6,"computed_at":"2026-10-07T05:47:15Z"}},"role":"Data Science","role_family":"Data Science","seniority":"middle","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":15500,"max_usd":38000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":13},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Databricks","optional":false},{"name":"Edge AI","optional":false},{"name":"Embeddings","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GitHub","optional":false},{"name":"Jira","optional":false},{"name":"Knowledge Graph","optional":false},{"name":"Machine Learning","optional":false},{"name":"NLP","optional":false},{"name":"NLTK","optional":false},{"name":"NumPy","optional":false},{"name":"Pandas","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Reranking","optional":false},{"name":"Scikit-learn","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-09-28T06:50:19Z","employer_posted_date":"2026-09-28","last_verified_at":"2026-10-08T00:06:45Z","board_verified":true,"closed_at":null,"days_open":9,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":9},"description":"Required Skills and Experience:\nBachelor's or Master's degree in a quantitative field (CS, machine learning, mathematics, statistics) or equivalent experience.\n3+ years of experience in data science, building hands-on ML models.\nCandidate must be aware of entire evolution history of NLP (Traditional Language Models to Modern Large Language Models), training data creation, training set-up and finetuning\nKnowledge of advanced RAG pipelines with proper embeddings, indexing, chunking, reranking, prompts and evaluation\nExcellent programming skills in Python. Strong working knowledge of Pythons numerical, data analysis, or AI frameworks such as NumPy, Pandas, Scikit-learn, Jupyter, etc\nSQL skills with SQL Server and Spark experience is preferred but not necessary.\nKnowledge of predictive/prescriptive analytics including Machine Learning algorithms (Supervised and Unsupervised) and deep learning algorithms and Artificial Neural Networks\nExperience with Natural Language Processing (NLTK) and text analytics for information extraction, parsing and topic modeling.\nExcellent verbal and written communication. Strong troubleshooting and problem-solving skills. Thrive in a fast-paced, innovative environment\nExperience with cloud platforms such as Azure, AWS, Databricks is preferred\nKey Responsibilities:\n3+ years of experience as a NLP and Python developer.\nExperience with Pandas, NumPy, Scikit, NLP a must have\nKey fundamentals in object-oriented design, data structures and systems.\nAbility to integrate multiple data sources into a single system.\nFamiliarity with testing tools.\nAbility to collaborate on projects and work independently when required.\nWorking knowledge of GitHub and Jira\nAbility to document requirements and specifications.\nDevelop and maintain advanced Python-based applications in the Generative AI domain, ensuring high performance, reliability, and scalability.\nImplement and optimize Generative AI models, including GPT, LLAMA, Mistral, FLAN T5 and other cutting-edge AI technologies, to create innovative solutions and knowledge graph.\nDevelopment of advanced RAG pipelines with proper embeddings, indexing, chunking, reranking, prompts and evaluation\nCollaborate with cross-functional teams to integrate AI functionalities into broader systems and applications.\nUtilize AWS/Azure/Databricks GPU machines to manage GPU memory effectively, maximizing performance and efficiency.\nStay updated on the latest advancements in Generative AI, Python development practices, and cloud services to continually enhance our AI capabilities.\nAssist delivery leads in delivering Generative AI solutions to clients in a timely manner, ensuring client satisfaction and project success.\n Bachelor's/Master's in Engineering 2-5 years","description_format":"text","description_chars":2749,"description_truncated":false,"requirements":{"experience_years_min":3,"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":[],"lifecycle":[{"event":"open","at":"2026-10-01T20:44:33Z"}],"visa":[],"liveness":{"score":27,"band":"fade","label":"Fading","p_open":1,"p_active":0.493,"p_room":0.55,"age_days":8,"expected_fill_days":6,"reasons":["conf:1","stale_co","wave","velocity","win:tail","comp:brand"],"computed_at":"2026-10-07T05:47:15Z"},"pay":null,"html_url":"https://alion.io/job/exl-data-scientist-2","json_url":"https://alion.io/job/exl-data-scientist-2.json","meta":{"generated_at":"2026-10-08T00:38:09Z","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":942,"day_limit":5000,"remaining_today":4058,"minute_limit":60,"resets_at":"2026-10-09T00:00:00Z"}},"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":38016},"rest":"https://alion.io/mcp/rest/get_company?id=38016"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fexl-data-scientist-2"},{"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%2Fexl-data-scientist-2"},{"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%2Fexl-data-scientist-2"},{"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/exl-data-scientist-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fexl-data-scientist-2"}]}