The main purpose of this thesis is to explore the use of computational techniques such as machine learning and genetic algorithms in peptide design. Peptides, short amino acid chains, have a wide variety of biomedical applications. They are used in drug design and as drug delivery systems. Peptide design is an expensive and time-consuming process because it requires high-throughput screenings together with experimental validation, which require a lot of time and resources. Machine learning and genetic algorithms, which will be reviewed in this thesis, can be used to design peptides faster and cheaper by programming the computer to do the work of designing for us. In addition, peptide properties that are important for their function will be reviewed. Basic physico-chemical properties are being used by computer algorithms to predict and/or optimise a peptide with a wanted trait. Some of these traits are antimicrobial or antiviral activity and can be used in applications such as the design of a new type drug based on peptides. Peptide design with computational techniques is a newly emerging field of study and most of the examples considered are of newer date. For this reason, this thesis aims to spread the knowledge about peptides and peptide design.