Pyspark, Kafka, Sql, Azure Data Factory, Terraform, Spark, Databricks, Azure, Python, MLflow, Unity Catalog, GitHub Actions, Microsoft Purview, Event Hubs, Delta Lake, Structured Streaming, Bicep

Data Transformation, Pyspark, Sql, Git, Pandas, Docker, FastAPI, Python, LangChain, vector databases, Azure AI Agent Service, embedding-based retrieval, LangGraph, multi-agent workflows, agentic AI systems, LLM-powered applications

snowflake , Pyspark, Containers, Sql, Flask, Databricks, FastAPI, Azure, Python, LangChain, CI CD monitoring, LLMs, Cloud platforms, Claude, retrieval optimisation, GPT, LangGraph, Agentic AI, tool-calling architectures, Streamlit, RAG pipelines, OpenAI, agent orchestration

snowflake , Java, Hadoop, Scala, Sql, Hive, Gcp, Docker, Spark, Databricks, Azure, Kubernetes, Python, AWS, Airflow, GitHub Actions, dbt

Testing, Debugging, Python, async programming, Reinforcement Learning with Human Feedback, software best practices, Supervised Fine-Tuning

Deduplication, Git, Pytorch, Linux, Python, dataset quality, Data Processing, machine learning pipelines, Hugging Face, LLM prompting, data leakage prevention, structured outputs, LLM fine-tuning, experiment configurations, retrieval, GPU environments, Annotation