Senior Generative AI Engineer (Edge Deployment with C++)

Key Responsibilities:

• Design, develop, and implement generative AI models (Transformers for text/image/audio generation) from research prototypes to production-ready systems.
• Optimize and deploy generative AI models on various edge devices (e.g., mobile, IoT, embedded systems, specialized AI accelerators) using C++ and relevant optimization techniques.
• Collaborate closely with research and Development Teams to identify, evaluate, and adapt novel generative AI architectures for edge deployment.
• Implement efficient inference pipelines, leveraging techniques such as model quantization, pruning, compilation, and hardware-specific optimizations.
• Develop and maintain robust C++ libraries and frameworks for model inference and integration on edge platforms.
• Conduct performance profiling, benchmarking, and debugging of AI models on target hardware.
• Contribute to the entire machine learning lifecycle, from data preprocessing and model training to deployment and monitoring.
• Stay up to date with the latest advancements in generative AI, edge computing, and C++ best practices.
• Mentor junior engineers and contribute to a culture of technical excellence.

Key Skills and Qualifications:

Strong Generative AI Skills (Must-Have):

• Deep understanding of Generative AI architectures: Extensiveexperience with and theoretical knowledge of various generative models, including:
• Autoregressive models for sequence generation (e.g., GPT, BERT, T5)
• Hands-on experience with popular deep learning frameworks: Proficiencyin at least one of the following, with a strong preference for PyTorch:
• PyTorch
• TensorFlow
• Model Training and Evaluation:Proven ability to train, fine-tune, and evaluate generative models, including understanding of metrics relevant to generative tasks (e.g., FID, Inception Score, perceptual metrics).
• Data Generation and Manipulation:Experience with synthetic data generation, data augmentation, and managing large datasets for generative tasks.
• Understanding of Latent Spaces:Strong intuition and practical experience working with and manipulating latent spaces.

C++ for Edge Deployment (Must-Have):

• Proficient C++ Programming:Excellent command of modern C++ (C++11/14/17/20) with strong software engineering principles, including memory management, data structures, and algorithms.
• Edge AI Frameworks/Libraries:Experience with C++-based inference engines and deployment tools for edge devices, such as:
• ONNX Runtime
• TensorRT
• OpenVINO
• TFLite (C++ API)
• Core ML (for iOS/macOS deployment)
• Performance Optimization:Demonstrated experience in optimizing C++ code for performance, including multi-threading, SIMD instructions, and understanding of cache coherence.
• Embedded Systems/Hardware Interaction:Familiarity with the constraints and challenges of deploying on embedded systems, including limited memory, power, and computational resources.

Good to have Skills :

• Experience with specific AI accelerators (e.g., NVIDIA Jetson, Google Coral, Qualcomm AI Engine).
• Knowledge of low-level hardware programming or system-on-chip (SoC) architectures.
• Experience with real-time systems and low-latency applications.
• Familiarity with MLOps practices for deploying and managing AI models in production.
• Contributions to open-source generative AI projects or relevant C++ libraries.
• Experience with other programming languages relevant to AI/ML (e.g., Python for prototyping).
• Strong understanding of computer vision or natural language processing fundamentals.

Education & Experience:

• Masters or Ph.D. in Computer Science, Electronics Engineering, or a related field with a specialization in Machine Learning, Artificial Intelligence, or Computer Vision with 5+ years of experience
• Alternatively, Bachelors degree with [7+] years of industry experience in a similar role focusing on Generative AI and C++ for edge deployment.