Role:Sr. Machine Learning Engineer (Data Science) Experience Level: 5+ Years Employment type:Full Time Location: California Role Summary Quantiphi is seeking a Sr. Machine Learning Engineer with strong data science expertise to support an AI agents engagement with a leading global technology distribution and solutions company. This role will focus on developing intelligent forecasting models and quotation automation agents on Google Cloud Platform (GCP). The ideal candidate combines deep statistical modeling skills with production ML engineering to deliver data-driven agentic AI solutions that drive operational efficiency across the client's distribution ecosystem. Key Responsibilities - Design, develop, and deploy forecasting models (time-series, demand forecasting, regression-based) for product demand, pricing trends, and quotation accuracy using GCP-native services (Vertex AI, BigQuery ML). - Conduct exploratory data analysis (EDA), feature engineering, and hypothesis testing on large-scale distribution and supply chain datasets to surface actionable insights for AI agent decision logic. - Build AI agents for forecasting and quotation workflows using agentic frameworks (LangChain, Vertex AI Agents, CrewAI) with data-driven decision-making capabilities embedded in agent reasoning. - Develop and maintain production ML pipelines on Vertex AI Pipelines and Cloud Composer for model training, evaluation, deployment, and retraining automation. - Implement statistical experimentation frameworks (A/B testing, causal inference) to validate model improvements and measure business impact of forecasting agents. - Collaborate with data engineering teams to design feature stores and data pipelines in BigQuery and Cloud Storage that feed forecasting and quotation models. - Optimize model performance through hyperparameter tuning, cross-validation, ensemble methods, and model interpretability techniques (SHAP, LIME) for stakeholder transparency. - Integrate ML model outputs into agentic workflows, enabling agents to autonomously generate, validate, and refine quotations based on real-time market and inventory data. - Document model architectures, experiment results, and agent decision logic; present findings and recommendations to client stakeholders and Quantiphi leadership. - Contribute to MLOps best practices including model versioning, drift detection, monitoring dashboards, and automated alerting using Vertex AI Model Monitoring. Required Qualifications - 6+ years of experience in machine learning engineering and data science, with a strong portfolio of deployed forecasting or predictive models. - Proficiency in Python (Pandas, NumPy, scikit-learn, statsmodels) and at least one deep learning framework (TensorFlow, PyTorch, or JAX). - Hands-on experience with GCP ML stack: Vertex AI (Training, Prediction, Pipelines), BigQuery, Cloud Functions, Cloud Storage, and Pub/Sub. - Strong foundation in statistics, probability, and time-series analysis (ARIMA, Prophet, exponential smoothing, state-space models). - Experience building or integrating with AI agent frameworks (LangChain, LlamaIndex, Vertex AI Agents, or similar agentic orchestration tools). - Proficiency in SQL for complex analytical queries on large-scale data warehouses. - Experience with experiment tracking and model management tools (MLflow, Vertex AI Experiments, Weights & Biases). - Bachelor's or Master's degree in Computer Science, Statistics, Mathematics, or a related quantitative field. Preferred Qualifications - Google Cloud Professional Machine Learning Engineer or Professional Data Engineer certification. - Experience in supply chain, distribution, or logistics domain with demand forecasting use cases. - Familiarity with LLM fine-tuning, prompt engineering, and retrieval-augmented generation (RAG) patterns for enterprise AI agents. - Prior consulting or professional services experience with client-facing delivery in an Agile environment. Engagement Details Client Industry: Global Technology Distribution & Solutions Delivery Partner: Quantiphi (an AI-First Digital Engineering company) Cloud Platform: Google Cloud Platform (GCP) Engagement Type: Professional Services / Consulting Delivery Location: Remote with potential onsite travel as required Duration: Contract engagement aligned with project milestones