Data Science Engineer

Data Science Engineer
Location:Remote within 100 miles of Culver City or Cupertino, CA
Schedule
: 40 hours
Duration
:18months
Pay
:$75/hr-$80/hrDOE

The Planet Group is looking for a Data Science Engineer to join our well-known Fortune 500 client on a 18-month contract, working a remote schedule.

• Marketing ML modelling:Proven experience building and deploying ML models for marketing use cases, including time-series forecasting, effort/resource estimation, and media-mix style response curve and diminishing-returns(saturation) modelling. Strong understanding of marketing performance concepts such as budget allocation, marginal efficiency, pacing and incrementality.
• Python and statistics: Strong Python skills (pandas, Num Py, scikit-learn, stats models, and a forecasting or probabilistic modelling library such as Prophet, PyMC or Stan). Sound grounding in statistics and experimentation,including uncertainty quantification, backtesting and model validation.
• End-to-end ML delivery: Hands-on experience building and operating batch ML pipelines in Apache Airflow(scheduling, backfills, data quality checks, retraining). Demonstrated ability to own the full model lifecycle independently,from concept to production, including feature engineering, model versioning, drift monitoring and retraining feedback loops.
• Gen AI components: Good understanding of developing Gen AI components, including:
  • MCP servers and tool design, with a governed semantic layer for natural-language data access
  • LLM agents, tool-calling workflows, prompt engineering and structured output
  • LLM evaluation frameworks (golden datasets, LLM-as-judge, regression testing)
  • Vector databases and embeddings for RAG, and entity resolution across systems
• Data foundations: Working knowledge of SQL and data warehouses (e.g., Redshift).
• Communication and collaboration: Ability to explain model assumptions, trade-offs and results to technical and non-technical stakeholders, and to work effectively with analytics SMEs.

• Experience developing services and APIs in Python
• PySpark for large-scale feature processing
• Bayesian modelling
• Optimization and constrained budget allocation techniques

• Design, build and product ionize the machine learning and Gen AI components behind
  
  Marketing's media planning, campaign estimation and intelligence products.
• Develop forecasting, estimation and marketing response models, including budget-allocation recommendations built on response curves and diminishing-returns analysis.
• Build Gen AI components, including MCP servers, agents, retrieval and entity resolution, with evaluation frameworks to keep LLM output reliable and consistent.
• Work independently, taking models from concept through to production. That covers problem framing, feature engineering, model development, validation, deployment as Python services and Airflow pipelines, and ongoing monitoring and retraining.
• Collaborate with internal analytics SMEs to shape modelling approaches and validate results.
• Be a primary point of contact for ML engineering support during business hours (PST).