diff --git a/mlir/include/mlir-c/ExecutionEngine.h b/mlir/include/mlir-c/ExecutionEngine.h
--- a/mlir/include/mlir-c/ExecutionEngine.h
+++ b/mlir/include/mlir-c/ExecutionEngine.h
@@ -36,9 +36,12 @@
 /// expected to be "translatable" to LLVM IR (only contains operations in
 /// dialects that implement the `LLVMTranslationDialectInterface`). The module
 /// ownership stays with the client and can be destroyed as soon as the call
-/// returns.
-/// TODO: figure out options (optimization level, etc.).
-MLIR_CAPI_EXPORTED MlirExecutionEngine mlirExecutionEngineCreate(MlirModule op);
+/// returns. `optLevel` is the optimization level to be used for transformation
+/// and code generation. LLVM passes at `optLevel` are run before code
+/// generation.
+/// TODO: figure out other options.
+MLIR_CAPI_EXPORTED MlirExecutionEngine mlirExecutionEngineCreate(MlirModule op,
+                                                                 int optLevel);
 
 /// Destroy an ExecutionEngine instance.
 MLIR_CAPI_EXPORTED void mlirExecutionEngineDestroy(MlirExecutionEngine jit);
diff --git a/mlir/lib/Bindings/Python/ExecutionEngine.cpp b/mlir/lib/Bindings/Python/ExecutionEngine.cpp
--- a/mlir/lib/Bindings/Python/ExecutionEngine.cpp
+++ b/mlir/lib/Bindings/Python/ExecutionEngine.cpp
@@ -59,17 +59,20 @@
   // Mapping of the top-level PassManager
   //----------------------------------------------------------------------------
   py::class_<PyExecutionEngine>(m, "ExecutionEngine")
-      .def(py::init<>([](PyModule &module) {
+      .def(py::init<>([](PyModule &module, int optLevel) {
              MlirExecutionEngine executionEngine =
-                 mlirExecutionEngineCreate(module.get());
+                 mlirExecutionEngineCreate(module.get(), optLevel);
              if (mlirExecutionEngineIsNull(executionEngine))
                throw std::runtime_error(
                    "Failure while creating the ExecutionEngine.");
              return new PyExecutionEngine(executionEngine);
            }),
+           py::arg("module"), py::arg("opt_level") = 2,
            "Create a new ExecutionEngine instance for the given Module. The "
-           "module must "
-           "contain only dialects that can be translated to LLVM.")
+           "module must contain only dialects that can be translated to LLVM. "
+           "Perform transformations and code generation at the optimization "
+           "level `opt_level` if specified, or otherwise at the default "
+           "level of two (-O2).")
       .def_property_readonly(MLIR_PYTHON_CAPI_PTR_ATTR,
                              &PyExecutionEngine::getCapsule)
       .def("_testing_release", &PyExecutionEngine::release,
diff --git a/mlir/lib/CAPI/ExecutionEngine/ExecutionEngine.cpp b/mlir/lib/CAPI/ExecutionEngine/ExecutionEngine.cpp
--- a/mlir/lib/CAPI/ExecutionEngine/ExecutionEngine.cpp
+++ b/mlir/lib/CAPI/ExecutionEngine/ExecutionEngine.cpp
@@ -10,22 +10,42 @@
 #include "mlir/CAPI/ExecutionEngine.h"
 #include "mlir/CAPI/IR.h"
 #include "mlir/CAPI/Support.h"
+#include "mlir/ExecutionEngine/OptUtils.h"
 #include "mlir/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.h"
 #include "llvm/ExecutionEngine/Orc/Mangling.h"
 #include "llvm/Support/TargetSelect.h"
 
 using namespace mlir;
 
-extern "C" MlirExecutionEngine mlirExecutionEngineCreate(MlirModule op) {
-  static bool init_once = [] {
+extern "C" MlirExecutionEngine mlirExecutionEngineCreate(MlirModule op,
+                                                         int optLevel) {
+  static bool initOnce = [] {
     llvm::InitializeNativeTarget();
     llvm::InitializeNativeTargetAsmPrinter();
     return true;
   }();
-  (void)init_once;
+  (void)initOnce;
 
   mlir::registerLLVMDialectTranslation(*unwrap(op)->getContext());
-  auto jitOrError = ExecutionEngine::create(unwrap(op));
+
+  auto tmBuilderOrError = llvm::orc::JITTargetMachineBuilder::detectHost();
+  if (!tmBuilderOrError) {
+    llvm::errs() << "Failed to create a JITTargetMachineBuilder for the host\n";
+    return MlirExecutionEngine{nullptr};
+  }
+  auto tmOrError = tmBuilderOrError->createTargetMachine();
+  if (!tmOrError) {
+    llvm::errs() << "Failed to create a TargetMachine for the host\n";
+    return MlirExecutionEngine{nullptr};
+  }
+
+  // Create a transformer to run all LLVM optimization passes at the
+  // specified optimization level.
+  auto llvmOptLevel = static_cast<llvm::CodeGenOpt::Level>(optLevel);
+  auto transformer = mlir::makeLLVMPassesTransformer(
+      /*passes=*/{}, llvmOptLevel, /*targetMachine=*/tmOrError->get());
+  auto jitOrError = ExecutionEngine::create(
+      unwrap(op), /*llvmModuleBuilder=*/{}, transformer, llvmOptLevel);
   if (!jitOrError) {
     consumeError(jitOrError.takeError());
     return MlirExecutionEngine{nullptr};
diff --git a/mlir/test/CAPI/execution_engine.c b/mlir/test/CAPI/execution_engine.c
--- a/mlir/test/CAPI/execution_engine.c
+++ b/mlir/test/CAPI/execution_engine.c
@@ -48,7 +48,7 @@
   // clang-format on
   lowerModuleToLLVM(ctx, module);
   mlirRegisterAllLLVMTranslations(ctx);
-  MlirExecutionEngine jit = mlirExecutionEngineCreate(module);
+  MlirExecutionEngine jit = mlirExecutionEngineCreate(module, /*optLevel=*/2);
   if (mlirExecutionEngineIsNull(jit)) {
     fprintf(stderr, "Execution engine creation failed");
     exit(2);