Senior, Software Engineer
Job description
About the role
This role connects offline perception data with online model training for automated truck perception systems. The work transforms pseudo-labeled sensor data into training-ready inputs. You will own the design and implementation of data ingestion and curation pipelines that bridge offline datasets and online training jobs. The position requires deep collaboration with perception and data science teams to ensure data quality and accessibility. You will drive improvements in data flow efficiency and support the evaluation of tooling against strategic objectives. Clear communication of data quality issues and technical trade-offs is a core part of the contribution. You will standardize deployment and related processes through developed guidelines and standards for the team.
Key facts
What you'll do
Online perception teams train models on demand using a supported ML data delivery system.
Less experienced team members are guided across multiple workstreams by a project lead demonstrating project management skills.
Large, multi-faceted datasets are governed through defined ingestion, preparation, curation, and workflows to support analytics and ML training.
Improvement areas are identified by proactively assessing current capabilities against strategy and operations.
Visualization and data accessibility for customers are enhanced through produced information products.
Productivity, quality, flow times, and operational surety are improved by evaluating and recommending technical advances.
Data quality control, data delivery systems, deployment, and related processes are standardized through developed guidelines and standards.
Production-grade Python code is written, and cloud-based development environments, CI systems, and containerized workflows are used effectively.
PyTorch, Lightning, or Ray experience is required for distributed data processing or ML frameworks.
Mastery of data pipeline and MLOps tooling, including ML frameworks, experiment tracking, model registry, and evaluation tools is expected.
Large-scale data curation methods, especially using Parquet processing tools, are handled with hands-on experience.
Responsibilities include mentoring engineers in the group while driving design, maintenance, and ownership of solutions across team interfaces.
You will write tests, fix bugs, and improve performance as part of regular engineering practices in small, focused teams.
The role involves planning, code review, and debugging, balancing these activities with focused periods of new code development.
Requirements
A Bachelor's Degree in Computer Science, Robotics, Electrical Engineering, or a related technical field with 6+ years of experience is required, or a Master's Degree with 3+ years of experience.
Complex work is conducted with minimal supervision, demonstrating high proficiency and independent judgment.
Design, maintenance, and ownership of solutions are driven across team interfaces while mentoring engineers in the group.
Mastery of data pipeline and MLOps tooling, including ML frameworks, experiment tracking, model registry, and evaluation tools is expected.
Large-scale data curation methods, especially using Parquet processing tools, are handled with hands-on experience.
Production-grade Python code is written, and cloud-based development environments, CI systems, and containerized workflows are used effectively.
PyTorch, Lightning, or Ray experience is required for distributed data processing or ML frameworks.
Practical notes
US authorization may be required, and candidates must meet degree or experience criteria.
The role may involve office-specific expectations, travel, or project-based assignments as defined by the team.
Typical interview steps
Hiring for engineering roles usually starts with a recruiter screen, followed by one or two technical rounds. Candidates often solve a coding problem, discuss past projects, and answer system design questions. Some loops include a take-home task. Final rounds typically cover team fit and give candidates a chance to ask questions. Interviewers look for how you break down an unfamiliar problem, not just whether you reach the answer. Practicing a few problems aloud and reviewing your own past projects are the best preparation.
Good to know
The role works with sensor data such as images and point clouds for perception tasks.
Data pipelines, MLOps, and scalable data curation tools are central to the work.
The position contributes to autonomous truck software within a commercial freight context.
Statistical analysis and clear communication of data quality issues are core responsibilities.
The team uses version control and documentation to manage evolving data and model requirements.