Network function virtualization (NFV) has drawn much attention in recent years, where some network functions that used to be deployed on specific hardware have become virtualized instances on general servers to achieve more scalability and flexibility. In a data center, service function chaining (SFC) makes a workflow traverse different network functions in a specific order to provide different levels of service for its customer. Because the distance between any adjacent network functions in a service chain will decide the total bandwidth consumption for that chain, the placement of the virtualized network functions in a data center becomes an important problem. In this study, this placement problem is treated as a multi-layer bin packing problem. Two greedy algorithms are proposed for the tree-like network topology: Multi-layer Worst-Fit (MWF) and Multilayer Best Fit (MBF). Furthermore, the placement problem is formulated as an integer linear programming. The experimental results show that MWF can reduce bandwidth consumption by 15% while only increasing the number of used servers by 1% compared to the traditional Best-fit algorithm.