Data Science & ML Engineer

Job Description:
Data Science & Analytics & Machine Learning for Power Commodity Trading
Focus is on the Data Science

1. Core Qualifications
Master's or PhD in Data Science, Computer Science, Finance, Engineering, or Applied Mathematics
5+ years of experience in machine learning or advanced analytics, with at least 2 years in energy, power, or commodities markets
Proficiency in Python (pandas, NumPy, scikit-learn, PyTorch, TensorFlow) and SQL
Experience deploying production-grade ML and analytics systems in AWS, Azure, or Google Cloud Platform
Strong foundation in statistics, linear algebra, and optimization

2. Domain Expertise – Power & Commodities:
Understanding of power market dynamics (generation, transmission, demand forecasting, ISO/RTO markets such as PJM, ERCOT, MISO, CAISO)
Familiarity with trading instruments: DA/RT markets, FTRs, CRRs, PPAs, futures, and swaps
Knowledge of natural gas, renewables, and carbon markets
Experience modeling locational marginal prices (LMP), congestion, and portfolio risk
Understanding of regulatory and compliance data (FERC, EIA, ISO market data)

3. Machine Learning & AI Expertise
Experience with supervised, unsupervised, and reinforcement learning for market forecasting or optimization
Proficient in LLMs (GPT, Llama, Mistral) and RAG (Retrieval-Augmented Generation) pipelines for automating report generation, trade rationale summaries, or market insights
Hands-on experience fine-tuning or evaluating generative models for quantitative or text-based analytics
Familiarity with agentic AI frameworks (LangChain, LlamaIndex, CrewAI) for autonomous data gathering, analysis, and decision support
Strong understanding of feature engineering, model interpretability, and bias control

4. Agentic & Autonomous Decision Systems
Experience creating intelligent trading assistants or agent frameworks that monitor, forecast, and act based on real-time data
Familiarity with planning, memory, and multi-agent collaboration concepts
Implementation of guardrails and ethical constraints in autonomous AI systems

5. Forecasting & Quantitative Modeling
Time series modeling (ARIMA, Prophet, LSTM, XGBoost) for price, load, or renewable generation forecasting
Optimization and scenario modeling for trading positions, hedges, or dispatch strategies
Proficiency with stochastic modeling, Monte Carlo simulations, and VaR analysis
Ability to integrate weather data, grid conditions, and market signals into predictive systems

6. Data Infrastructure & Engineering
Strong data architecture skills: ETL/ELT pipelines, dbt, Airflow, or Prefect
Experience with data warehouses (DataBricks, Snowflake)
Familiarity with vector databases (FAISS, Pinecone, Weaviate) for retrieval-augmented analytics
Data governance awareness: versioning, lineage, security, and compliance

7. Analytics, Visualization & Communication
Strong experience with dashboards and visualization tools (Power BI, Tableau, Plotly)
Ability to design KPIs and visual analytics for trading performance, market exposure, and forecast accuracy
Experience building automated insight pipelines or LLM-based analytics assistants
Skilled in translating technical findings into clear narratives for traders and executives