Simulation & Autonomy Systems Architect

Grid Dynamics; United States; Remote; USD 180.000 - 250.000; Vollzeit

Zusammenfassung

Grid Dynamics is seeking an experienced Simulation & Autonomy Systems Architect to lead the autonomy stack from prototype to a deployable product at customer sites. This remote role with pre-approved client-site travel will own simulation strategy, safety cases, and fast reactive safety layers, while mentoring a small, fast-moving team.

You will coordinate across perception, planning, and control, guide hardware/software integration, and define degradations and fallback paths for

Qualifikationen

• 10+ years in autonomous systems (robotaxi, autonomous trucking, mining, agriculture or construction autonomy)
• Hands-on ownership of behavior, planning or control software in a deployed autonomy stack
• Proven design of minimum-risk maneuvers, fallback trajectories and degraded modes of operation
• Simulation strategy for autonomy: integrating simulation into development and validation loop, with scenarios, sensor models and data contracts
• System safety practice: FMEA, hazard analysis and close work with functional safety teams (ISO 26262, ISO 21448 SOTIF or similar)
• Vehicle and powertrain dynamics for heavy machines: braking and traction limits under load, on slopes and in rough terrain
• Software architecture and hardware/software integration for real-time systems on embedded compute
• Strong hands-on coding skills in C++ and Python, with a track record of using AI coding agents to accelerate development and problem-solving
• Heavy-duty or off-road autonomy, such as trucks, mining haul or construction equipment
• End-to-end learned driving or VLA models, and how to wrap them in safety envelopes
• Field and rapid-response engineering: fast fixes from field issues

Aufgaben

• Own the program's simulation strategy: how simulation feeds autonomy development and validation, scenario coverage, and how real and simulated data are combined
• Lead failure analysis (FMEA and fault-tree analysis) across perception, planning and control and hardware, starting now rather than after launch
• Design degraded modes and minimum-risk conditions: health monitors, run levels, fail-operational versus fail-safe behavior, and fallback paths
• Architect fast reactive safety layers, such as collision-imminent braking that doesn't wait on the full perception pipeline, while keeping false positives low
• Define cross-cutting architecture outside any single team: software and hardware integration, interfaces and system-level features
• Work with safety engineering on a safety case: acceptable event rates for a given fleet and operating hours, and the signals to track to show due diligence
• Bridge hardware and software timelines: tell hardware teams which requirements must be fixed now and which can wait
• Write, review and guide code produced with AI coding agents inside guardrails such as automated tests and toolchain checks
• Lead the simulation workstream's contribution to the 2027 Program Charter and Roadmap, and guide the two Simulation & Perception architects on the team
• Mentor engineers and lead by example in a small, fast-moving team

Kenntnisse

C++

Python

Simulation

AI coding agents

Leadership

Mentorship

FMEA

Safety-critical

Autonomy systems

Fault-tree analysis

Tools

NVIDIA Omniverse

CARLA

NVIDIA Isaac Sim

Jobbeschreibung

We are seeking an experienced Simulation & Autonomy Systems Architect to lead the autonomy stack from a working prototype to a fully unsupervised product deployed at customer sites. In this key role, you will own our simulation strategy for rapid validation and architect the fault tolerance, graceful degradation, and safety cases required for mission-critical, real-world deployment. This is a remote role with pre-approved travel to client sites.

Essential functions

• Own the program's simulation strategy: how simulation feeds autonomy development and validation, scenario coverage, and how real and simulated data are combined.
• Lead failure analysis (FMEA and fault-tree analysis) across perception, planning, control and hardware, starting now rather than after launch.
• Design degraded modes and minimum-risk conditions: health monitors, run levels, fail-operational versus fail-safe behavior, and fallback paths that a simpler system can follow.
• Architect fast reactive safety layers, such as collision-imminent braking that doesn't wait on the full perception pipeline, while keeping false positives low.
• Define cross-cutting architecture outside any single team: software and hardware integration, interfaces and system-level features.
• Work with safety engineering on a safety case: acceptable event rates for a given fleet and operating hours, and the signals to track to show due diligence.
• Bridge hardware and software timelines: tell hardware teams which requirements must be fixed now and which can wait.
• Write, review and guide code produced with AI coding agents inside guardrails such as automated tests and toolchain checks.
• Lead the simulation workstream's contribution to the 2027 Program Charter and Roadmap, and guide the two Simulation & Perception architects on the team.
• Mentor engineers and lead by example in a small, fast-moving team.

Qualifications

• 10+ years in autonomous systems, such as robotaxi, autonomous trucking, mining, agriculture or construction autonomy.
• Hands-on ownership of behavior, planning or control software in a deployed autonomy stack.
• Proven design of minimum-risk maneuvers, fallback trajectories and degraded modes of operation.
• Simulation strategy for autonomy: integrating simulation into the development and validation loop, with scenarios, sensor models and data contracts between simulation and the autonomy stack (NVIDIA Isaac Sim, CARLA or equivalent).
• System safety practice: FMEA, hazard analysis and close work with functional safety teams (ISO 26262, ISO 21448 SOTIF or similar).
• Vehicle and powertrain dynamics for heavy machines: braking and traction limits under load, on slopes and in rough terrain.
• Software architecture and hardware/software integration for real-time systems on embedded compute.
• Strong hands-on coding skills in C++ and Python, with a track record of using AI coding agents to accelerate development and problem-solving.
• Heavy-duty or off-road autonomy, such as trucks, mining haul or construction equipment.
• End-to-end learned driving or VLA models, and how to wrap them in safety envelopes.
• NVIDIA Omniverse and synthetic data generation for training and testing.
• Field and rapid-response engineering: fast fixes from field issues.

Would be a plus

• Heavy-duty or off-road autonomy, such as trucks, mining haul or construction equipment.
• End-to-end learned driving or VLA models, and how to wrap them in safety envelopes.
• NVIDIA Omniverse and synthetic data generation for training and testing.
• Field and rapid-response engineering: fast fixes from field issues.
• Startup experience: doing more with less while managing several teams.
• Patents or publications in autonomy, safety or control.

About us

Grid Dynamics (NASDAQ: GDYN) is a leading provider of technology consulting, platform and product engineering, AI, and advanced analytics services. Fusing technical vision with business acumen, we solve the most pressing technical challenges and enable positive business outcomes for enterprise companies undergoing business transformation. A key differentiator for Grid Dynamics is our 8 years of experience and leadership in enterprise AI, supported by profound expertise and ongoing investment in data, analytics, cloud & DevOps, application modernization and customer experience. Founded in 2006, Grid Dynamics is headquartered in Silicon Valley with offices across the Americas, Europe, and India.