Most problems in system design have multiple objectives and constraints. For example, a company that makes a smartphone needs to increase battery life, minimize system lag, and maximize system bandwidth. Solutions to these design problems are given by the trade-off among the different competing objectives. Many recent works assign weights to the objectives to determine their importance. However, assigning weights requires domain expertise or a trial-and-error method that leads to significant cost increases and long development times. INFORM (our method) uses artificial intelligence (AI) to augment human creativity when designing a system with multiple objectives and constraints. We first discover the trade-off among competing objectives that does not require determining the importance of each objective. Next, we focus only on the solutions of interest to the designer and enhance their performance. Our method thus speeds up the design time (up to 17x) and avoids wasting computational resources. In contrast to existing methods that use forward model to optimize a system, we use inverse design. Inverse design utilizes the desired system response to perform targeted optimization. INFORM can also drive an existing solution to another solution with different specifications. Driving a solution to another specification allows a designer to have a generic system prototype and adapt it using INFORM for various customer needs. INFORM does not use GPUs, which presents a sustainable design technique. Instead, we utilize multiple CPU cores to speed up optimization. INFORM also improves the value of the objective function by up to 30% compared to a state-of-the-art method.