Computer Vision Engineer

Key Responsibilities

Multidisciplinary Team Leadership

o Lead an engineering team to build out , scaling the perception organization pipelinecomprising Robotics, CV/ML, Data, Software, Embedded, and Integration engineering disciplinesby aligning technical efforts, resolving cross-functional challenges, and driving mission-focused execution

o Own hiring, mentoring, and infrastructure investments critical to team success.

o Maintain hands-on technical oversight while optimizing performance, driving innovation, and ensuring stakeholder clarity.

Full-Stack Perception System Ownership

o Manage the perception technology roadmap, systems architecture, and product execution, leveraging robotics, CV/ML, and high-quality software engineering to bring state-of-the-art solutions to market

o Prototype system concepts, validate hypotheses, and contribute to product roadmaps

o Conduct system analysis to identify bottlenecks and propose architectural or algorithmic improvements

o Evaluate and integrate new technologies, frameworks, and accelerators based on program requirements

Leading the Perception Software Development Team comprising of the following responsibilities:

o Engineer high-quality software systems and integration architecturethe core of this teamincluding:

Architecting end-to-end perception systems spanning edge platforms and GCS infrastructure to provide operators with comprehensive situational awareness.

Integration of third-party software and sensor systems with the perception stack.

Validation of system integration with the autonomy stack across simulated and operational environments

o Develop sensor data acquisition and preprocessing methodologies encompassing sensor data handling, interpretation, and synchronization; sensor control including configuration, rates, and gimbal behavior; and image processing techniques

o Develop, optimize, deploy, and maintain perception models including CV/ML architectures such as object detection, segmentation, tracking, and Vision Language Models; complementary image processing techniques including image matching and Structure from Motion; deployment on edge devices (such as NVIDIA SOCs) with performance optimization; secure development practices across the ML deployment lifecycle; and data curation and maintenance workflows MLOps.

o Apply robotics engineering methodologies to define perception-driven robot behaviors such as desired platform trajectories, sensor parameters, and multi-robot target search strategies.

Required Qualifications

Bachelor's or Master's degree in Computer Science, Electrical Engineering, or related field.

Proven expertise in C++/Python and designing reliable software systems.

Technical Leadership: Demonstrated leadership in guiding a multidisciplinary team, with hands-on contributions in core areas and clear technical direction in others.

Perception Systems and Software Engineering:

o Proven ability to own and evolve an end-to-end perception pipeline (from sensors through inference to output translation), collaborating with specialists for advanced model development, MLOps, or embedded optimization as needed.

o Comfortable working across edge devices and backend systems.

o Proficiency integrating third-party libraries, sensor SDKs, and external frameworks.

o Ability to identify bottlenecks, propose architectural improvements, and validate solutions through simulation and testing.

ML/CV and Systems Knowledge:

o Working knowledge of modern architectures, training pipelines, and model optimization

o Understanding of MLOps concepts, data curation, and model lifecycle management

Domain Depth:

o Deep expertise in at least one of: edge deployment (NVIDIA SOCs), MLOps/ML pipelines, or robotics/UAV/autonomous vehicles perception systems

o Ability to learn and operate competently in adjacent domains

Desired Skills

Familiarity with UAV systems or real-time autonomy stacks.

Familiarity with ROS or robotics frameworks.

Background in secure coding or Secure SDLC processes.

Experience in algorithms for multi-robot coordination and behaviors.

Vision Language Models, or advanced geometric computer vision algorithms.

Experience with Active Learning, Domain Adaptation, or edge-platform porting.