Actually I’m talking about .NET Core. That Docker image is built on Debian Jessie, and it installs Hadoop and .NET Core. You can run compiled .NET Core assemblies just by running
dotnet /path/to/my/assembly.dll. The same image can run as Hadoop master and worker nodes, so all workers have .NET Core installed and can run .NET Core apps.
Which means you can run .NET Core apps as mappers or reducers in Hadoop jobs, thanks to theHadoop Streaming interface. Hadoop Streaming lets you shell out to any program the host can execute, to run the tasks for your job. Your code integrates with Hadoop at a basic level – through the standard input and output streams.
Elton has some good courses on other Hadoop-and-.NET topics (like his HDInsight deep dive course). It looks like running containerized Hadoop + .NET Core is getting closer, but still has room for improvement.