Senior Perception Engineer

ABOUT AIM INTELLIGENT MACHINES Curious if you want to terraform earth? Everything humanity depends on is mined, dug, or grown. At AIM, we are building the autonomous linchpin of civilization. We transform heavy machinery—bulldozers, loaders, excavators—into AI-powered fleets that operate continuously, safely, and at peak performance in the world’s harshest environments. AIM runs production mines, large scale infrastructure builds, and defense operations as a TRL9 hardened system, not a science experiment. We have been automating this massive space with embodied AI and emerged as the market choice for ground engagement autonomy. Built by engineers from mining, construction, Waymo, SpaceX, Google and Tesla, AIM enables scalable earthmoving, turbocharging the global economy’s physical foundation. AIM is backed by some of the most sophisticated capital in the world, including General Catalyst, Khosla Ventures, Elad Gil, Human Capital, Ironspring Ventures, Mantis, DCVC. ABOUT YOU You’re an engineer who loves solving difficult perception problems where machine learning meets the physical world. You have experience building production machine learning systems that operate on real hardware, not just in research environments. You understand how perception algorithms behave under real-world constraints such as sensor noise, environmental variability, limited compute, and incomplete data. You enjoy working across the full perception stack - from sensor data ingestion and calibration, through model development and training, to deployment on edge compute and real-time inference pipelines. You take ownership of outcomes, not just models. You debug deeply, validate rigorously, and iterate quickly using field data to continuously improve system performance. You’re motivated by building perception systems that enable safe, reliable autonomy in environments where failure is not acceptable. As a Senior Perception Machine Learning Engineer, you will design, develop, and deploy the perception systems that allow AIM’s autonomous machines to understand and interact with their environment. Design & Advance Perception Systems - Architect and develop perception algorithms for scene understanding, obstacle detection, terrain modeling, and machine awareness. - Advance AIM’s perception stack including sensor fusion, environment modeling, and machine-centric perception pipelines. - Develop algorithms that operate reliably in complex, dynamic earthmoving environments. Build Production Machine Learning Systems - Develop and deploy machine learning models for perception tasks including object detection, segmentation, depth estimation, and terrain understanding. - Optimize models for real-time inference on edge compute platforms. - Build scalable data pipelines for training, evaluation, and model iteration. Integrate Perception with the Autonomy Stack - Collaborate with robotics, controls, systems, and software teams to integrate perception outputs into planning and control systems. - Ensure perception systems interact correctly with localization, SLAM, mapping, and safety systems. - Design perception interfaces that are robust, testable, and observableResponsibilities - Advance AIM’s perception stack and sensor fusion algorithms - This involves breaking new ground as earth moving machines don’t merely navigate on existing mapped roads – they modify and build the environment as they work which poses interesting novel challenges - Research and development of state-of-the-art machine learning methods - Comfortable with hands-on applications on machines deployed in the field - Apply real-world experience with localization and SLAM state-of-the-art methods QUALIFICATIONS Core ML Fundamentals - Experience designing, training, and evaluating machine learning models - Strong understanding of the mathematics behind training (optimization, gradients, regularization, bias–variance tradeoff) - Familiarity with training dynamics (overfitting, underfitting, convergence iss