AI Data Engineer

AI Data EngineerWe are looking for an AI Data Engineer with strong experience in Data Engineering and hands-on knowledge of ML/LLM technologies.ResponsibilitiesBuild and maintain production-level data pipelines using Python, PySpark, and cloud technologies.Convert Data Science/ML solutions into scalable production pipelines.Develop and implement LLM and RAG solutions using tools such as LangChain.Work with LLM APIs such as OpenAI, Azure OpenAI, AWS Bedrock, or similar.Optimize distributed data processing and Spark workloads.Implement CI/CD pipelines for data and ML applications.Implement schema validation, data quality checks, and pipeline monitoring.Evaluate LLM applications using metrics such as retrieval quality, answer correctness, relevance, and faithfulness.Troubleshoot and optimize production data and AI pipelines.Required SkillsStrong Data Engineering experience.Hands-on ML/LLM experience is a must.Experience with Python, PySpark, SQL, and distributed processing.Experience with RAG and LangChain or similar frameworks.Experience integrating LLM APIs.Experience with CI/CD and production deployments.Knowledge of data validation, data quality, and pipeline optimization.Experience with LLM evaluation and quality metrics.