{"id":2782109,"url":"https://alion.io/job/coditation-data-scientist","title":"Data Scientist","company":{"id":4442667,"name":"Coditation","domain":"coditation.com","url":"https://alion.io/company/coditation","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Keka","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":20000,"max_usd":41000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":59},"experience_years_min":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Amazon Redshift","optional":false},{"name":"AWS","optional":false},{"name":"Databricks","optional":false},{"name":"GCP","optional":false},{"name":"Kedro","optional":false},{"name":"LangChain","optional":false},{"name":"LightGBM","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"NLP","optional":false},{"name":"NumPy","optional":false},{"name":"pgvector","optional":false},{"name":"Polars","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Scikit-learn","optional":false},{"name":"SHAP","optional":false},{"name":"Snowflake","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"XGBoost","optional":false},{"name":"FastAPI","optional":true},{"name":"Flask","optional":true},{"name":"Machine Learning","optional":true},{"name":"RAG","optional":true}],"status":"live","first_seen_at":"2026-03-03T10:18:33Z","employer_posted_date":"2026-03-03","last_verified_at":"2026-10-17T23:02:18Z","board_verified":true,"closed_at":null,"days_open":228,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":228},"description":"Data Scientist\nPune\nAbout Us\nCoditation Systems was founded by a serial entrepreneur, and a team of young talented technologists, some ofwho have grown to spearhead the organization. With its inception in 2016, we became a boutique technologyservices and solutions firm specializing in Machine Learning & AI, Data Engineering, and Cloud. We have ateam of ninja architects, data scientists, data engineers, and software engineers having decades of collectiveexperience of applying emerging technologies to build cutting edge software products.\nWhat are we looking for?\nWe are looking for a skilled Databricks Developer with hands-on experience in building and optimizing data pipelines on the Databricks platform. The ideal candidate should have strong expertise in big data processing, Spark, and cloud data engineering, with the ability to work in a fast-paced, data-driven environment.\nA Day in the Life\nBuild and optimize predictive models for churn forecasting, revenue contraction, and risk analysis at customer-product levels.\nDevelop end-to-end data science libraries and orchestrate pipelines using Kedro, managing data loading, feature engineering, model training, inference, and explainability.\nDeploy AI/ML solutions on cloud platforms (GCP / AWS) and expose models as APIs.\nCollaborate with cross-functional teams to translate business requirements into technical solutions.\nMonitor data quality, detect drifts, and implement data governance frameworks.\nPerform image classification, text moderation, and other AI/ML-based solutions for client products.\nDesign, develop, and deploy LLM-based AI agents for business intelligence, automated workflows, and decision support.\nWhat you will need\n7+ years of experience in Data data science\nProgramming Languages: Python, SQL\nFrameworks & Libraries: scikit-learn, PyTorch, XGBoost, LightGBM, pandas, NumPy, Polars, LangChain, LlamaIndex, Crew.ai\nDatabases: Postgres (pgvector, tsvector), Redshift, Snowflake (and/or any other vector db)\nStrong understanding of data science workflows, including data cleaning, feature engineering, model selection, validation, and explainability (e.g., SHAP).\nExperience in developing chatbots or automated query systems.\nExperience in image classification and transformer-based NLP models.\nGood to have: Cloud & Platforms: GCP, API deployment using Flask / FastAPI\nGood to have: Experience with RAG, LLM prompt optimisation, and GraphLLMs to reduce hallucinations.\nCompetencies\nProven track record of end-to-end ML project delivery, from raw data to production.\nStrong analytical skills with experience in clustering, forecasting, and predictive modeling.\nExperience working with subscription and contractual business models.\nAbility to optimize LLMs and ML models for performance, latency, and scalability.\nExcellent problem-solving and communication skills.","description_format":"text","description_chars":2849,"description_truncated":false,"requirements":{"experience_years_min":7,"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":[],"lifecycle":[{"event":"open","at":"2026-10-17T13:14:21Z"}],"visa":[],"liveness":{"score":8,"band":"cold","label":"Long shot","p_open":1,"p_active":0.277,"p_room":0.28,"age_days":228,"expected_fill_days":37,"reasons":["conf:2","win:tail","crowd:"],"computed_at":"2026-10-18T01:05:16Z"},"pay":null,"html_url":"https://alion.io/job/coditation-data-scientist","json_url":"https://alion.io/job/coditation-data-scientist.json","meta":{"generated_at":"2026-10-18T01:05:16Z","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":1792,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-19T00:00:00Z"}},"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":4442667},"rest":"https://alion.io/mcp/rest/get_company?id=4442667"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcoditation-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%2Fcoditation-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%2Fcoditation-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/coditation-data-scientist\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcoditation-data-scientist"}]}