In this study, two genetic algorithms (GAs) that design the layouts of beams, slabs, and columns of rectilinear floors are developed. A rectilinear floor is a polygonal floor, all of whose edges meet at right angles. The two proposed algorithms are to be used in sequence. From an architectural floor plan with given positions of walls, the first algorithm designs the beam-slab layout of the floor. Using the solution of the first algorithm, the second algorithm designs the column layout. The development of each of the two layout design algorithms begins with the construction of a representative optimization problem for that layout design problem. Both beam-slab and column layout design problems are heuristic but their representative optimization problems must be algorithmic in order that each can be solved by a GA. It is therefore necessary that both layout design problems be converted into algorithmic ones. In this study, a methodology to convert a heuristic design task into an algorithmic design task is established. In the methodology, a prioritized list of required and desirable characteristics of design solutions is first heuristically created. From the prioritized list, an order relation that specifies how to compare two design solutions is defined. The representative optimization problem of the design problem is thereafter created by using the obtained order relation. The representative optimization problem is subsequently prepared in a form that is suitable for a genetic algorithm in order to finally create the final algorithm. The proposed methodology to convert a heuristic design problem into an algorithmic design problem is used to develop the representative optimization problems for beam-slab layout design and column layout design. Two similar GAs are thereafter developed to solve both representative optimization problems. The proposed GAs are tested with several column-beam-slab layout design problems, and satisfactory results are observed.