Proper assessment of geometric features of a thermoelectric generator is important to design devices with improved performance features such as high efficiency and output power. In the present study, three the-state-of-the-art multi-objective evolutionary algorithms, namely, NSGA-II (Non-dominated Sorting Genetic Algorithm-II), GDE3 (Generalized Differential Evolution generation 3), and SMPSO (Speed-constrained Multi-objective Particle Swarm Optimization) are used to optimize the geometric features of a thermoelectric generator for improved efficiency and output power while incorporating different operating conditions. The parameters assessing geometric features of the device include shape factor and pin length size while operating parameters include temperature ratio and external load parameter. Thermal analysis incorporating geometric features and operating parameters of the device is introduced prior to the optimization study. The findings are validated against the results reported in the open literature. It is found that shape factor and pin length size have significant effect on the device performance. Increasing shape factor (S <= 0.5) first increases thermal efficiency to reach its maximum (similar to 17%), and furthermore, an increase in shape factor (S >= 0.5) lowers thermal efficiency significantly (similar to 8%). Device output power behaves similar to that of efficiency for small increment in shape factor, provided that further increase in shape factor does not influence output power of the device. A unique design configuration is present for a fixed operating condition of a thermoelectric generator; in which case, thermal efficiency and output power of the device attain high values. (C) 2014 Elsevier Ltd. All rights reserved.