{"id":1514117,"url":"https://alion.io/job/stratzi-ai-data-scientist","title":"Data Scientist","company":{"id":4474,"name":"Stratzi.ai","domain":"stratzi.ai","url":"https://alion.io/company/stratzi-ai","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":null,"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":14500,"max_usd":35000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":13},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Embeddings","optional":false},{"name":"LLM","optional":false},{"name":"MLFlow","optional":false},{"name":"NumPy","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"RAG","optional":false},{"name":"Scikit-learn","optional":false},{"name":"SQL","optional":false},{"name":"Structured Outputs","optional":false},{"name":"TensorFlow","optional":false},{"name":"Time Series Forecasting","optional":false},{"name":"Weights & Biases","optional":false},{"name":"Fine-tuning","optional":true},{"name":"LLM Guardrails","optional":true}],"status":"live","first_seen_at":"2026-09-30T08:56:24Z","employer_posted_date":null,"last_verified_at":"2026-09-30T08:56:24Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"We're looking for a Data Scientist to build production-grade models on large-scale industrial and railway/metro telemetry data. You'll work across time-series forecasting, anomaly detection, predictive maintenance, and Applied GenAI, helping engineering and control-room teams detect failures earlier and make operational knowledge easier to access.\nResponsibilities:\nBuild forecasting models for energy, traction power, load profiles, and operational planning.\nDevelop anomaly detection for multivariate sensor and telemetry streams.\nBuild predictive maintenance and Remaining Useful Life (RUL) models.\nWork with real-world industrial data, including missing/stale tags, sensor drift, irregular sampling, and limited failure labels.\nApply signal processing techniques such as spectral analysis, wavelets, and feature extraction.\nBuild RAG systems over maintenance records, incident reports, O& M manuals, and engineering standards.\nUse LLMs/GenAI for structured extraction from work orders, fault logs, and operational reports.\nPrototype text-to-SQL / natural-language interfaces for operational data.\nDesign evaluation frameworks covering accuracy, grounding, refusal behavior, and reliability.\nDeploy and monitor models in production, including drift detection and retraining.\nRequirements:\n4+ years of applied data science experience with models deployed in production.\nStrong expertise in time series, including ARIMA/SARIMAX, ETS, state-space models, gradient boosting, and deep learning approaches such as LSTM/GRU, TCN, or transformers.\nExperience with forecasting and anomaly detection on sensor/telemetry data.\nHands-on GenAI/LLM application development: RAG, embeddings, vector databases, prompt engineering, structured outputs, and evaluation.\nStrong Python and SQL skills.\nProficiency with pandas, NumPy, scikit-learn, and PyTorch/TensorFlow.\nStrong statistical fundamentals, temporal validation, leakage prevention, and uncertainty quantification.\nExperience with MLOps and tools such as MLflow, Weights and Biases, or similar.\nAbility to collaborate closely with domain/engineering teams and translate domain knowledge into modelling features and constraints.\nGood to Have:\nExperience with industrial/sensor data.\nRailway or metro domain experience.\nPredictive maintenance, reliability engineering, RCM/FMEA/RAMS/survival analysis.\nExperience with time-series foundation models such as Chronos, TimesFM, or Moirai.\nLLM fine-tuning, agent frameworks, guardrails, or safety tooling.\nExplainability and experience deploying models for operational users.\nExperience working in regulated engineering environments.","description_format":"text","description_chars":2623,"description_truncated":false,"requirements":{"experience_years_min":4,"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":["Predictive Analytics","AI Consulting & Integration"],"lifecycle":[{"event":"open","at":"2026-09-30T08:56:24Z"}],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":17,"reasons":["seen:0","win:early"],"computed_at":"2026-10-01T04:09:23Z"},"pay":null,"html_url":"https://alion.io/job/stratzi-ai-data-scientist","json_url":"https://alion.io/job/stratzi-ai-data-scientist.json","meta":{"generated_at":"2026-10-01T04:09:23Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":3351,"day_limit":5000,"remaining_today":1649,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}