Senior Data Engineer - AI

• Contribute to the data architecture, design, and deployment of scalable Generative AI and Machine Learning systems into production environments.
• Develop end-to-end GenAI features, including backend API services, model integration, model monitoring, evaluations, and deployments.
• Integrate and optimize LLMs for specific business planning use cases, including prompt engineering and RAG implementation.
• Design and build the retrieval and knowledge layer powering our RAG and agentic workloads, such as vector databases, graph databases, knowledge graphs, hybrid search, and embedding pipelines.
• Help design the knowledge graph that captures the semantics of customer models, metrics, hierarchies, and relationships.
• Build the data plane for evaluation and continuous improvement, working with cutting-edge conversational and agentic AI technologies.
• Engineer the feature and context pipelines that feed forecasting and anomaly-detection models at customer scale, balancing batch and streaming patterns.
• Implement evaluation frameworks to measure and improve GenAI feature quality, including accuracy, latency, and user satisfaction metrics.

• Extensive data engineering experience with a track record of delivering complex projects.
• Hands-on experience building and shipping AI/ML products in production.
• Practical experience with LLM-based systems: RAG architectures, embedding pipelines, prompt and response logging, and evaluation frameworks.
• Hands-on expertise with vector databases, graph databases, and knowledge graphs.
• End-to-end exposure to the model development lifecycle, including experience training and deploying ML models in production environments.
• Solid knowledge of LLM APIs, prompt engineering, and conversational AI patterns.
• Strong expertise in MLOps and LLMOps, ensuring scalable, reliable, and monitorable model deployments.
• Proficiency in Python and modern software development practices (testing, code review, CI/CD).

• Hands-on experience with cloud-native ML infrastructure platforms.
• Knowledge of vector databases (e.g., Pinecone, Weaviate, Qdrant) and embedding models.
• Experience with model serving frameworks (e.g., vLLM, TensorRT, Ray).
• Background in forecasting, planning, or analytics applications.
• Experience with A/B testing and experimentation frameworks for AI features.
• Experience with model observability tools (e.g., LangSmith, W&B, MLflow).

#LI-SP1