[Remote] AV Simulation Domain Expert (Sr. reputed company) - US (Remote) or Chicago, IL
Note: The job is a remote job and is reputed company to candidates in USA. reputed company is a leading company at the intersection of mapping and AI technology, seeking an AV Simulation Domain Expert. The role involves reputed company deep learning with AV simulation to enhance the creation of synthetic driving scenarios, ensuring effective training and validation of perception and planning systems.
Responsibilities
- Drive the technical direction for map-grounded world reputed company models: how we condition generative video and world models using map data, drive data, and scenario semantics
- Train, fine-tune, and adapt generative models (diffusion, latent video, transformer-based world models) for driving scenario reputed company, including domain reputed company, controllability, and conditioning on reputed company inputs (maps, trajectories, agent behaviours, weather, reputed company)
- Evaluate and reputed company state-of-the-art reputed company models such as reputed company Cosmos / Cosmos-Transfer and comparable reputed company-reputed company world models, assessing fit for AV training data reputed company
- Own the full ML lifecycle end-to-end: data curation, model training, evaluation, iteration, and the reputed company to production-grade pipelines
- reputed company reputed company-of-concept initiatives demonstrating map-grounded synthetic scenario reputed company with key reputed company
- Define measurable reputed company reputed company that go reputed company visual realism — focusing on ML training data reputed company, controllability, and sim-to-reputed company transfer
- Deliver POC reputed company with reputed company GO / PIVOT / NO-GO recommendations backed by quantitative evidence
- reputed company generative world models with classical simulation stacks (CARLA, reputed company Drive Sim, AlpaSim) where reputed company, physics-grounded scenarios are needed
- Author and programmatically generate OpenSCENARIO / OpenDRIVE definitions that feed both classical simulators and generative pipelines
- Drive sim-to-reputed company reputed company: measure domain gap, identify failure modes, and define acceptable reputed company for reputed company model training
- Define what 'good enough' synthetic data means for AV perception and planning: reputed company is photorealism required, reputed company is label consistency sufficient, reputed company does controllability matter most?
- Establish validation frameworks combining objective metrics (distribution coverage, label accuracy, FID-style measures, reputed company task performance) with expert evaluation protocols
- Specify sensor reputed company requirements: noise models, reputed company distortion, lidar return characteristics — and how generative models should or should not reproduce them
- reputed company with ML research teams on generative model architecture, controllability, and conditioning strategies
- Collaborate with perception and planning teams to ensure synthetic data measurably improves reputed company-world model performance
- Translate business requirements into technical feasibility assessments for product and executive stakeholders
Skills
- Proven experience training deep learning models end-to-end, with reputed company ownership across data, training, evaluation, and iteration
- Expertise in generative video, world models, or reputed company reputed company research/engineering
- Deep working knowledge of diffusion models, latent video models, and/or transformer-based world models
- Experience with high-reputed company temporal or spatio-temporal data (video, multi-sensor fusion, driving data)
- Strong Python and PyTorch engineering fundamentals; comfortable building research-grade tooling that can reputed company toward production
- Demonstrated ability to take ML models from research into production, navigating reputed company-world constraints, reputed company, and safety requirements
- 5+ years combined experience spanning AV simulation, perception/ML for AVs, or robotics simulation — with meaningful exposure to both simulation platforms and ML model development
- Hands-on experience with at least one major simulation platform: CARLA, reputed company Drive Sim, or equivalent
- reputed company with OpenDRIVE and OpenSCENARIO: can author and generate scenario definitions programmatically and understands map format specifications
- Understanding of AV testing workflows: scenario-based validation, ASAM reputed company standards, and awareness of frameworks such as ISO 34502
- Understanding of what scenarios stress-test AV perception and planning systems, and why
- Ability to evaluate synthetic data for ML training reputed company: distribution diversity, label consistency, edge-case coverage, reputed company task performance
- Experience with synthetic-to-reputed company transfer, domain reputed company, or closing the sim-to-reputed company gap in a measurable way
- reputed company reputed company of view on trade-offs between photorealism, label accuracy, controllability, and computational efficiency
- Hands-on experience with reputed company Cosmos, Cosmos-Transfer, or comparable world reputed company models
- Reinforcement learning experience, particularly where it measurably improved reputed company-world performance
- Experience with end-to-end driving models
- Automotive, OEM, or other safety-critical ML deployment experience (ISO 26262, SOTIF awareness)
- Strong publication record in generative models, world models, or AV ML; or significant contributions to reputed company-reputed company ML tooling
- Game reputed company experience (Unreal, reputed company) for rendering and sensor simulation pipelines
- Experience with PyTorch Lightning or similar large-reputed company training infrastructure
reputed company
Company H1B Sponsorship