Automation Engineer, Robotics Autonomy Resume

Starting...

Automation Engineer, Robotics Autonomy Resume Mateusz Cole Automation Engineer, Robotics Autonomy (619) 555-2847 mateusz.cole@example.com linkedin.com/example/mateuszcole San Diego, CA 92101 STRENGTHS Production Diagnosis Tracing one difficult robot event through logs and model outputs revealed a system issue, not a model defect. Evaluation Design Field failures became focused datasets and regression cases, giving modeling peers clearer evidence for decisions. Hardware Validation Physical robot tests exposed behavior that offline metrics missed, so rollout evidence became more dependable. Cross Team Work Data, modeling, robotics, and field partners received practical findings they could act on quickly. Quiet Reliability Careful notes and repeatable scripts often solved small inconsistencies before they became production problems. SKILLS Python C++ PyTorch Machine learning Robotics Autonomous systems Perception Prediction Planning Learned navigation Model training Model fine tuning Model evaluation Data labeling Model deployment LANGUAGES English Native 40 Spanish Intermediate 20 MY CAREER 6.7 Years Automation Engineer, Robotics Autonomy at Northstar Mobile Robotics (2.9 Years) Machine Learning Robotics Engineer, Autonomy Systems at VectorPath Autonomy (2.2 Years) Junior Robotics Software Engineer, Autonomous Systems at Canyon Robotics Lab (8 Months) Robotics Engineering Associate, Autonomous Systems at Granite Motion Systems (11 Months) SUMMARY Automation Engineer with six years improving machine learning and autonomy systems for robots operating beyond controlled laboratory settings. Production work covers failure triage, perception and planning evaluation, dataset development, model fine tuning, deployment validation , and physical robot testing. Uses Python, PyTorch, and C++ to trace difficult behavior through telemetry, logs, sensor traces, model outputs , and system interactions. Builds evaluation sets from field failures, refines labeling guidance, and checks whether improvements generalize across customer sites. Partners closely with modeling, data labeling, robotics, and deployment teams, turning production observations into reproducible tests and practical engineering changes. Brings thoughtful debugging, hands on autonomy experience, and a steady focus on dependable operation for customers using real world robotic systems. EXPERIENCE Automation Engineer, Robotics Autonomy Northstar Mobile Robotics October 2023 - Present San Diego, CA Owns autonomy triage for mobile robots in logistics facilities, supporting production reliability, customer use cases, model evaluation , and staged deployment. Leads evidence based collaboration across modeling, data, robotics, and field operations teams. Reconstructed production failures from telemetry , logs , sensor traces, and model outputs for focused autonomy diagnosis Built failure review workflow grouping field events by behavior, impact, evidence, and acceptance criteria Created PyTorch evaluation datasets from occlusions, aisle geometry, and unusual traffic interactions for model comparison Fine tuned models with curated examples and regression sets, checking site gains against broader fleet behavior Integrated inference updates with C++ robotics components, validating physical robots before staged production deployment Supported customer use cases from prototype through live operation, converting observations into practical system changes Machine Learning Robotics Engineer, Autonomy Systems VectorPath Autonomy July 2021 - September 2023 Oceanside, CA Developed perception and prediction experiments for autonomous material handling robots, combining Python, PyTorch , labeled sensor sequences, hardware validation, and deployment tooling. Supported repeatable decisions across modeling, data , and field engineering functions. Developed perception and prediction experiments with Python and PyTorch against labeled sensor sequences Designed dataset slices around false detections and trajectory errors for focused field condition comparison Traced preprocessing, inference, and downstream C++ consumers to resolve timing and interface failures Established reproducible evaluation runs recording dataset versions, configurations, and representative failures for deployment decisions Worked with field engineers during hardware validation to reproduce observations under realistic robot motion Standardized model artifacts and configuration checks, reducing mismatches between evaluated and deployed robot versions Junior Robotics Software Engineer, Autonomous Systems Canyon Robotics Lab October 2020 - June 2021 Temecula, CA Supported supervised development of an autonomous mobile robot stack through log analysis, C++ integration, labeled scenario preparation, hardware testing, and repeatable documentation. Quiet improvements gave engineering teams clearer evidence during difficult debugging sessions. Implemented Python utilities for robot logs and sensor data during navigation debugging Extended C++ components under senior review, improving data flow between perception and planning interfaces Prepared labeled scenario sets covering obstacles, localization uncertainty, and constrained navigation paths Ran repeatable hardware tests after software and model updates, comparing behavior with scenario outcomes Built analysis scripts that surfaced recurring error patterns across robot test runs Maintained experiment, dataset, and configuration notes so findings stayed reproducible across teams Robotics Engineering Associate, Autonomous Systems Granite Motion Systems October 2019 - September 2020 Escondido, CA Supported indoor autonomous robot prototype development through Python testing, C++ changes, sensor recording, telemetry analysis, and machine learning data preparation. Built early habits around careful evidence collection and practical hardware validation. Supported an indoor autonomous robot prototype with Python utilities and small C++ changes Collected sensor recordings from laboratory and warehouse trials with timestamps and configuration details Executed perception and planning test plans on physical hardware, documenting regressions across repeated scenarios Created telemetry scripts that reduced manual inspection across builds and experimental configurations Prepared data subsets for machine learning experiments and checked labels against sensor sequences Coordinated test evidence with robotics and machine learning engineers during integration reviews PROJECTS Site Failure Evaluation Pipeline 2024 Created a reusable workflow for converting deployed robot failures into labeled datasets, regression cases, and acceptance criteria. Connected telemetry review with model evaluation and deployment validation across site specific scenarios. Learned Navigation Regression Study 2022 Evaluated learned navigation behavior against curated sensor sequences and physical robot trials. Compared model candidates across recurring trajectory errors, unusual traffic, and constrained paths before deployment decisions. LEADERSHIP & AWARDS Recognized by robotics and deployment peers for turning difficult production failures into reproducible evaluation cases. Selected by engineering leadership to support customer use cases from prototype validation through live robot operation. Trusted reviewer for model artifacts, dataset versions, and physical robot rollout evidence. EDUCATION Bachelor's Degree in Computer Science California State University San Marcos GPA: 3.5 2019 San Marcos, CA Coursework: Machine Learning, Robotics, Data Structures, Algorithms, Software Engineering CERTIFICATIONS Deep Learning Specialization 2021 C++ Programming for Robotics 2020 TECHNICAL SKILLS Programming Languages: Python, C++, Bash Machine Learning Frameworks: PyTorch, TensorFlow, scikit learn Autonomy Functions: Perception, prediction, planning Data Engineering: ML data pipelines, dataset curation, data labeling Model Operations: Model training, model fine tuning, model evaluation Robot Systems: Autonomous systems, learned navigation, sensor fusion Production Diagnostics: Telemetry analysis, log analysis, model outputs Deployment Validation: Model deployment, rollout validation, rollback criteria Testing Methods: Regression testing, scenario testing, hardware validation Software Integration: Inference integration, C++ interfaces, configuration checks SKILLS Python C++ PyTorch Machine learning Robotics Autonomous systems Perception Prediction Planning Learned navigation Model training Model fine tuning Model evaluation Data labeling Model deployment PROFESSIONAL AFFILIATIONS Robotics Industries Association, professional member focused on deployed autonomy. Association for Computing Machinery, computing professional member. LANGUAGES English (Native) Spanish (Intermediate) ADDITIONAL INFORMATION Work Status : Authorized to work in United States. No sponsorship required. ADDITIONAL INFORMATION Work Status : Authorized to work in United States. No sponsorship required. REFERENCES AVAILABLE ON REQUEST

File
- Open
- Save
- Save As
- Rename
- PDF Page Setup
- Preview
- PDF Download
- Show Styles
Preview
Show Styles
PDF Download
US English

US English

UK English

Spanish (LatAm)

French

German

Japanese

Italian

Portuguese (BR)

Chinese (Simplified)
Log In