ML Engineer, II - Perception

About the Company

At Torc, we have always believed that autonomous vehicle technology will transform how we travel, move freight, and do business.

A leader in autonomous driving since 2007, Torc has spent over a decade commercializing our solutions with experienced partners. Now a part of the Daimler family, we are focused solely on developing software for automated trucks to transform how the world moves freight.

Join us and catapult your career with the company that helped pioneer autonomous technology, and the first AV software company with the vision to partner directly with a truck manufacturer.

Meet the Team

Torc Sim is the simulation platform built by our Dataloop + Simulation division to help Autonomy teams replay, recompute, evaluate, and visualize their models against real and synthetic driving data at scale. It is the backbone that turns a logged drive into a repeatable, measurable experiment, and we are working to scale our impact across all our Autonomy users.

We are hiring a Machine Learning Engineer to sit at the center of that growth: reporting to Dataloop + Simulation but living day-to-day with one or two Autonomy teams to drive Torc Sim adoption from the inside. You will be the person who makes sure a model team's replay/recompute jobs run at scale, that the metrics coming out are interpretable and auditable, and that engineers can visualize what their model is doing.

Along the way, you will become the resident expert on whichever model you are partnered with, whether Perception or Behavior models, so you fluently translate between "simulation platform" and "autonomy model.”

What You'll Do

• Act as the embedded point of contact between Dataloop + Simulation and one to two Autonomy teams, driving hands-on adoption of Torc Sim
• Implement the end-to-end data flow: data ops platform → simulation environment → persistent storage running at scale
• Onboard Autonomy models to execute replay/recompute workflows at scale, as well as the subsequent metric evaluation
• Ensure adoption of the visualization tooling and bring back UI/UX improvements for our development backlog
• Become a domain expert on the model(s) your partner team owns (e.g., Camera, Lidar, Vehicle Intent, Object Tracking) so you can implement and own integrations
• Debug issues that span the full stack, from data ingestion, through simulation execution, to storage and metrics — and drive them to resolution
• Translate on-the-ground feedback from Autonomy engineers into concrete requirements for the Dataloop + Simulation product roadmap
• Document workflows and onboard new users so adoption scales beyond your own hands-on support

What You'll Need to Succeed

Bachelor’s Degree in Computer Science, Robotics, Electrical Engineering or related technical field plus demonstrates competences and technical proficiencies typically acquired through 4+ years of experience OR Master’s Degree in Computer Science, Robotics, Electrical Engineering or related technical field plus demonstrates competences and technical proficiencies typically acquired through 0-3+ years of experience.

• Strong Python skills and experience building or operating data pipelines at scale
• Experience working with simulation, replay, or model validation
• Familiarity with autonomy or robotics ML models (perception, tracking, prediction, or planning) and the data they consume
• Comfort working across cloud storage and compute
• Strong cross-team communication skills — you'll be translating between a platform team and one or two embedded Autonomy teams on a daily basis
• A bias toward hands-on problem solving: you're as comfortable debugging a broken data pipeline as you are explaining a metric discrepancy to a model owner

Bonus Points!

• Prior experience in a forward-deployed engineer, solutions engineer, or embedded platform role
• Hands-on experience with Camera, Lidar, Vehicle Intent, or Object Tracking models specifically
• Experience with simulation or replay frameworks for autonomous vehicles or robotics
• Familiarity with visualization tooling such as Foxglove, OpenGL, or Three.js
• Experience with large sensor data formats (MCAP, Parquet) and associated processing tools (PyArrow, Daft, Pandas)
• Experience with distributed compute/orchestration frameworks (Ray, Anyscale, AWS HyperPods)
• Infrastructure-as-code experience (Terraform) and CI systems (GitHub Actions)

Work Location:

For this position, we are hiring Remote in the United States and Canada.