Job Title: Senior AI Engineer
Location: Trivandrum
Job Type: Full-time
About the Role:
ZenturioTech is seeking a highly experienced Senior AI Engineer to lead the design, optimization, and deployment of AI models on embedded platforms. This role demands deep expertise in performance tuning, model compression, and edge AI systems.
Primary Responsibilities:
-
Design and develop AI/ML-based applications with a focus on embedded hardware (e.g., Renesas RZ/V2H, NVIDIA Jetson, STM32).
-
Port and optimize AI models for real-time performance on resource-constrained devices.
-
Perform quantization, pruning, and model conversion (ONNX, TensorRT, TVM, TFLite, DRP-AI).
-
Own end-to-end AI model lifecycle: data prep, training, validation, and inference optimization.
-
Customize AI architectures for specific edge AI tasks like object detection, classification, and segmentation.
-
Profile and debug model performance on target boards to meet latency and throughput goals.
Required Skills & Experience:
-
Minimum 5 years of experience in AI/ML development with strong deployment focus.
-
Proficient in Python and frameworks such as PyTorch, TensorFlow, or Keras.
-
Deep knowledge of CNNs, FCNs, and vision-based deep learning architectures.
-
Hands-on experience with model optimization techniques (quantization, pruning, INT8 calibration, etc.).
-
Proven experience deploying AI models on embedded hardware platforms.
-
Familiarity with OpenCV and tools like ONNX, TVM, TFLite, or custom inference engines.
What You'll Bring:
-
Expertise in building scalable and efficient AI pipelines for the edge.
-
Ability to guide junior team members and drive optimization strategy.
-
Strong problem-solving skills and a mindset for real-world deployment challenges.
How to Apply:
Send your resume to admin@zenturiotech.com with the subject line “Senior AI Engineer – Application”.