Why join Seegrid?
Seegrid is the leading provider of self-driving industrial vehicles. We develop and deliver mobile robots and enterprise software for global leaders in logistics, manufacturing, warehousing, and e-commerce. Our suite of solutions includes vision-guided vehicles, fleet management software, actionable analytics, and best-in-class service and support. Our unique and proven technology sets us apart—our automation solutions have safely driven millions of autonomous miles in real production facilities without a single personnel safety incident. We are seeking energetic, bright, and friendly people to help achieve our vision: to fortify global supply chains and create profitable economies with safe, seamless, and smart mobile robotics solutions.
The Role: Perception Data Engineer
As a Data Engineer on the Perception Team at Seegrid, you will be responsible for aggregating, curating, and organizing sensor data, as well as optimizing data pipelines and workflows to support the development of next-generation perception solutions on our industry leading industrial autonomous vehicles. You should be fluent in at least one programming language, and have broad exposure to college level math, statistics, and probability theory. To be successful in this role, you will need to be able to demonstrate initiative under minimal direction and be comfortable supporting the data needs of multiple groups, systems, and products. This role reports to a Technical Lead on the Perception Team.
Core Responsibility for this role:
The Perception Data Engineer will be responsible for expanding and optimizing our data and data pipeline architectures, as well as optimizing data flow and collection. These data will feed several workflows, to include automating software testing, incident troubleshooting, and machine learning (ML) model development on our fleet of industrial autonomous vehicles. This role also requires you continually recommend, develop, and implement process improvements and tools for collecting, analyzing, and visualizing data.
The successful completion of your first year, looks like:
- You have standardized Perception data formats for different sensors, organized and transformed existing datasets, and created a workflow/tools for others in the Perception team to do the same. All of this work has been socialized and is well documented.
- You have curated data sets as inputs for automated software testing pipelines.
- You have put into use best practices for preparing training, validation, and test data sets for use in ML model development.
- You have worked closely with Perception development engineers, and are capable of independently training an ML model suitable for deployment. At least one ML model that you supported is in production, and being deployed on Seegrid Autonomous Mobile Robots.
- You are able to triage perception related service tickets, and to perform the data analysis necessary to take them to completion.
Responsibilities will consist of:
- Expanding and optimizing our data and data pipeline architectures, as well as optimizing data flow and collection across the Perception Team’s Product, Development, and Data groups.
- Employing, extending, and authoring software tools to support data collection, analysis, and visualization.
- Leading data labeling efforts for our ML models, with an emphasis on automating approaches through programmatic labeling.
- Curating test data sets for inclusion into our automated software testing pipeline.
- Implementing processes and systems to monitor data quality and ensure data accuracy.
- Organizing historical field data to facilitate and (where possible) automate future incident troubleshooting.
- Triage perception-related service tickets that escalate to engineering and take them to resolution to ensure the highest levels of service for our customers
- BS in Computer Science, Engineering, Statistics, Mathematics or a related technical field
- Strong organizational and problem solving skills
- Team player with strong interpersonal skills
- Excellent written and verbal communication skills
- Fluent in one or more programming languages such as Python and/or C++
- Fluent in working with Linux, particularly on the command-line
- Familiarity with software version control systems (e.g., Git) and other software engineering best practices (e.g., unit testing, continuous integration, etc.)
- Previous experience in a Data Analyst/Data Engineer position
- 1+ years of experience working with programming languages such as Python, C++, SQL, or R
- 1+ years of experience working with databases, common sensor data serialization formats/tools (csv, json, HDF5, rosbag, etc.), and data pipelining tools
- Familiar with best practices for preparing training data for machine learning models
- Experience using containers (e.g., Docker)
- Robotics related experience
- Experience with ROS or ROS2
Seegrid is embracing a remote workforce, so this position can be remotely located anywhere in the US or at HQ in Pittsburgh, PA (preferred). We have been recognized regionally and nationally as a Best-Place-to-Work and we are proud of our 97% employee retention rate. We’d love to have you join us!
All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, protected veteran status, or disability status. Seegrid is an equal opportunity employer Minorities/Females/People with Disabilities/Protected Veterans/Sexual Orientation/Gender Identity.
Let us know
Help us maintain the quality of jobs posted on RemoteTechJobs and let us know if: