Portfolio

All AI services

FPT Automotive’s AI Engineering division bridges the gap between raw machine learning models and safety-critical automotive applications. Across 8 specialized AI service areas built for the automotive industry, we combine deep domain expertise (AUTOSAR, CAN-bus, ISO 26262) with modern deep learning and generative AI. Our portfolio spans the entire vehicle software lifecycle—optimizing edge-perception models for Qualcomm and NVIDIA SoCs, automating verification to compress testing loops, and implementing intelligent cockpit assistants. Use the tags below to filter our services and explore technical architecture diagrams, benchmarks, and success stories.

AI Chatbot

LLM-powered conversational AI for automotive trainee support, MBD engineering, factory operations, and warranty classification.

80%+

Trainee UAT accuracy

60%

Factory search reduction

2 stages

Warranty workflow automated

LLMNLPRAGMBD

In-Cabin AI Agent

Hybrid edge-cloud voice AI and CAN-bus predictive safety for next-generation digital cockpits.

1,241ms

Edge command path

4,596ms

Cloud path latency

3.06×

Faster than Tier-1 system

Voice AIDigital CockpitDriver MonitoringNLP

Data Analysis & ML

Predictive safety, driver context on Qualcomm, EV diagnostics, and drawing reviews powered by ML.

18.7×

Qualcomm inference speedup

3-15s

CAN predictive safety warning

70%

Drawing review setup cut

Machine LearningMBDModel Validation

Edge AI

Low-latency, privacy-first on-device AI for driver monitoring, hybrid voice, and smart manufacturing.

Sub-100ms

Qualcomm emotion inference

1,241ms

Telechips edge voice loop

2 seconds

Edge vision panel inspection

Edge ComputingMachine LearningDriver Monitoring

Physical AI

Autonomous driving VLMs, robotic manipulation benchmarking, and MLOps on Vertex AI.

250

robot episodes collected

100%

Model Garden integration

3-15s

CAN hazard pre-warning

Autonomous DrivingRoboticsMachine Learning

Refactoring AI

Automated code review, MISRA-C compliance, and safe API porting for SDV migrations.

90%

Review time reduction

2-3 hours

Review time per 100K LOC

80%

Defect coverage rate

LLMStatic AnalysisMISRA-CCode Review

System Test AI

AI-assisted end-to-end vehicle validation and HIL/SIL simulation compliance.

75%

Test execution time cut

ISO 26262

Functional safety compliance

18.7×

Inference speedup on hardware

ISO 26262Test AutomationAUTOSARFunctional Safety

Unit Test AI

AI unit test generation at 85-90% accuracy, virtualized execution, and MBD check-rule automation.

5-7 mins

Test case generation time

85-90%

Test generation accuracy

70%

MBD rule-check coverage

LLMTest GenerationMBDModel Validation