Handling ONNX/ML.NET models with generic interfaces

i'm kind of struggling with a ML.NET related problem here and am hoping that someone might can help me.

I'm developing an (.NET core) application which consumes ONNX models whose inputs are unknown at compile time. What I've done so far:

I'm able to compile an assembly during runtime which contains the input class definition and load this definition:

        var genericSampleAssembly =
            AssemblyLoadContext.Default.LoadFromAssemblyPath("/app/storage/sample.dll");
        Type genericInputClass = genericSampleAssembly.GetType("GenericInterface.sample");

Also I'm able to train a model with that dynamically created Inputtype using Reflection:

        MethodInfo genericCreateTextLoader = typeof(TextLoaderSaverCatalog).GetMethods()
            .Where(_ => _.Name == "CreateTextLoader")
            .Single(_ => _.GetParameters().Length == 6)
            .MakeGenericMethod(_genericInputClass);

        TextLoader reader = genericCreateTextLoader.Invoke(_mlContext.Data, new object[] { _mlContext.Data, false, ',', true, true, false}) as TextLoader;

        IDataView trainingDataView = reader.Read("sample.txt");
        var debug = trainingDataView.Preview();

        var pipeline = _mlContext.Transforms.Concatenate("Features", _featureNamesModel
            .AppendCacheCheckpoint(_mlContext)
            .Append(_mlContext.Regression.Trainers.StochasticDualCoordinateAscent(labelColumn: "Label",
                featureColumn: "Features")));

        ITransformer model = pipeline.Fit(trainingDataView);

But I'm not able to make predictions by now because I don't know how to invoke the PredictionEngine. I'm able to get a generic version of that CreatePredictionEngine method but don't now how to cast that returning object to an PredictionEngine and finally invoke the Predict method:

        MethodInfo genericCreatePredictionEngineMethod = typeof(PredictionEngineExtensions).GetMethods()
            .Single(_ => _.Name == "CreatePredictionEngine")
            .MakeGenericMethod(new Type[] { genericInputClass, typeof(GenericPrediction)});

        var predictionEngine = genericCreatePredictionEngineMethod.Invoke(_model, new object[] {_model, _mlContext, null, null});

predictionEngine is of Type object in this case but I need to cast it to something like PredictionEngine<genericInputClass, GenericPrediction>, while genericInputClass is the class from that dynamically created assembly and GenericPrediction is a simple class with one output I know at compile time.

So whats missing is something like:

        MethodInfo genericCreatePredictionEngineMethod = typeof(PredictionEngineExtensions).GetMethods()
            .Single(_ => _.Name == "CreatePredictionEngine")
            .MakeGenericMethod(new Type[] { genericInputClass, typeof(GenericPrediction)});

        PredictionEngine<genericInputClass, GenericPrediction> predictionEngine = genericCreatePredictionEngineMethod.Invoke(_model, new object[] {_model, _mlContext, null, null}) as PredictionEngine<genericInputClass, GenericPrediction>;

        float prediction = predictionEngine.Predict(genericInputClass inputValue);

Does anyone had a similar problem or has any other hints?

I might missed some lines, because I copy/pasted and simplified it pretty quick. In case something is missing, I'll provide it later.

Greetings Sven