Overview:
Blue Yonder is looking for a hands-on Machine Learning Engineer / Data Scientist (3–4 years of experience) to design, build, and deploy ML solutions that power intelligent decision-making across our supply chain and retail platforms. The primary focus is on production ML — forecasting, optimization, recommendations, and anomaly detection on structured tabular datasets.
As a secondary responsibility, the role will contribute to Generative AI initiatives (LLM-powered features, RAG pipelines, intelligent assistants) that complement our classical ML stack. This is not a research role — we are looking for someone who has shipped ML systems to production and can own problems end-to-end.
What you'll do:
Design, develop, and deploy ML models for forecasting, classification, regression, recommendations, and anomaly detection use cases across supply chain and retail.
Build and maintain end-to-end ML pipelines — feature engineering, training, evaluation, inference, and monitoring — using modern MLOps tooling.
Translate ambiguous business problems into well-defined ML problems with clear success metrics.
Design and analyze experiments (A/B tests, offline evaluations) to quantify model and business impact.
Monitor models in production for drift and performance degradation, drive retraining cycles.
Contribute to GenAI features — RAG pipelines, LLM-powered assistants, summarization/extraction — using prompt engineering, retrieval strategies, and evaluation frameworks (groundedness, faithfulness, hallucination rate).
Partner with product, data engineering, and domain experts to take ideas from POC to production.
What we are looking for:
Required Skills:
Python-Pandas, scikit-learn, NumPy, production-quality scripting
Machine Learning-Classification, regression, clustering, anomaly detection
SQL-Querying and working with relational databases
Model Evaluation-Cross-validation, metrics, bias/variance tradeoff
Data Wrangling-Handling real-world messy tabular data
Big Data: Spark / PySpark, Snowflake / BigQuery, or similar; feature engineering at scale.
Cloud & MLOps: Hands-on with at least one cloud platform (Azure / AWS / GCP); experience with MLflow, Airflow, SageMaker, Vertex AI, or Azure ML.
Deployment: REST APIs, batch pipelines, or real-time inference; familiarity with Docker and basic Kubernetes.
DevOps: Git, GitHub (Actions, CI/CD), branching strategies, and code-review discipline.
LLMs & RAG: Working knowledge of LLM APIs (Azure OpenAI, OpenAI, Anthropic), RAG architectures, embeddings, and vector databases (FAISS, Pinecone, Azure AI Search, pgvector).
Frameworks: Exposure to LangChain, LangGraph, or LlamaIndex.
Evaluation: Understanding of GenAI evaluation metrics; experience with Langfuse or Ragas is a plus.
Good to Have:
Advanced ML: XGBoost, LightGBM, Isolation Forest, or ensemble methods.
Time Series: ARIMA, Prophet, or modern deep-learning forecasting approaches.
MLOps depth: MLflow for experiment tracking and model lifecycle management.
GenAI delivery: Shipped at least one RAG or LLM-powered feature to production.
Our Values
If you want to know the heart of a company, take a look at their values. Ours unite us. They are what drive our success – and the success of our customers. Does your heart beat like ours? Find out here: Core Values
All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability or protected veteran status.