Website Yantran LLC
Yantran LLC
Company : Yantran LLC
We are seeking a Data Scientist with 9 or more years of hands on experience in data cleaning, transformation, and analysis using Python. The ideal candidate is comfortable working with large, messy datasets, has exposure to modern data technologies, and brings a strong analytical mindset. Experience with machine learning and LLMs is a strong plus.
Data scientists with proven time-series forecasting portfolios
Candidates from energy, utility, or renewable sectors
Profiles showing ARIMA/SARIMAX/Prophet/LSTM experience
Evidence of weather-dependent forecasting projects
Production deployment of operational forecasting systems
Key Responsibilities
Clean, preprocess, and transform structured and unstructured data using Python
Perform exploratory data analysis (EDA) to uncover insights and trends
Build reusable data pipelines and feature engineering workflows
Work with SQL and/or cloud based data warehouses to extract and prepare data
Collaborate with stakeholders to translate business problems into data driven solutions
Develop and maintain analytical models and dashboards
Apply basic to intermediate machine learning techniques where applicable
Experiment with and support LLM based solutions (prompting, embeddings, APIs) as needed
Ensure data quality, reliability, and documentation
Required Skills
Qualifications
9+ years of experience as a Data Scientist / Data Analyst
Strong proficiency in Python for data manipulation and analysisPandas, NumPy, SciPy
Solid understanding of data cleaning, transformation, and feature engineering
Experience with SQL (PostgreSQL, MySQL, BigQuery, Snowflake, etc.)
Familiarity with data visualization toolsMatplotlib, Seaborn, Plotly, or Power BI/Tableau
Understanding of statistics and data analysis fundamentals
Experience working with APIs and external data sources
Strong problem solving and communication skills
Modern / Latest Tech Stack (Preferred)
Python (3.x)
Pandas, NumPy, Scikit learn
Jupyter, VS Code
Git / GitHub
Cloud platforms: AWS / Azure / GCP
Data tools: Airflow, dbt, Spark (basic exposure)
Containerization: Docker (nice to have)
Good to Have
Hands on experience with Machine Learning modelsRegression, classification, clustering, time series
Exposure to LLMs and Generative AIOpenAI / Azure OpenAI APIs
Prompt engineering
Embeddings, vector databases (FAISS, Pinecone, Chroma)
Experience with NLP or text analytics
Knowledge of MLOps basics (model versioning, monitoring)