Optimize, compress, and distill large language and vision models for on-device inference. Build pipelines for distillation and hardware-specific compilation, and benchmark performance across NPU/GPU architectures.
We are looking for an AI Specialist Engineer to enhance the performance of large language and vision models for on-device inference. Your expertise will be crucial in developing and deploying cutting-edge AI solutions, ensuring optimal efficiency across diverse hardware architectures.
Responsibilities:
- Compress and optimize large language and vision models for on-device inference.
- Develop pipelines for model distillation and hardware-specific compilation.
- Benchmark performance across various NPU/GPU architectures.
Qualifications:
- Expertise in model distillation, pruning, and 4-bit/8-bit quantization techniques.
- Hands-on experience with TensorRT, ONNX Runtime, and edge deployment.
- Strong C++ and Python skills.
Similar Jobs
Agency • Artificial Intelligence • Blockchain • Web3
Run adversarial tests on language and multimodal models, build guardrails and real-time filters for autonomous tool use, and support RLHF alignment and constitutional AI development to ensure safe AI deployment.
Top Skills:
Adversarial MlGuardrailsJailbreak TaxonomiesLlmsMultimodal AgentsPrompt EngineeringReal-Time FilteringRed-Teaming FrameworksRlhf
.png){kind=logo}
AdTech • Cloud • Digital Media • Information Technology • News + Entertainment • App development
Create high-quality 3D character gameplay animations for navigation, interactions, conversations, traversal, and other gameplay systems. Export, implement, and test animations in the game engine; troubleshoot animation issues; collaborate with animators, designers, and gameplay programmers; participate in reviews; and mentor junior animators. The role requires strong knowledge of body mechanics, biped locomotion, motion capture, keyframe animation, gameplay systems, and animation workflows, with experience shipping an AAA game.
Top Skills:
Animation Blend SystemsAnimation GraphsKeyframe AnimationMayaMotion CaptureMotion MatchingMotionbuilderRiggingRoot MotionUnreal Engine
Cloud • Information Technology • Productivity • Security • Software • App development • Automation
Participate in a 15-week full-time software engineering internship in Vancouver, Burnaby, or Richmond. Build and ship product features, contribute code to Atlassian products, apply data structures and algorithms, and learn full-lifecycle development through mentorship and collaboration with senior engineers. Work may involve cloud initiatives and AI-driven features.
Top Skills:
CC++JavaPython
What you need to know about the Calgary Tech Scene
Employees can spend up to one-third of their life at work, so choosing the right company is crucial, not just for the job itself but for the company culture as well. While startups often offer dynamic culture and growth opportunities, large corporations provide benefits like career development and networking, especially appealing to recent graduates. Fortunately, Calgary stands out as a hub for both, recognized as one of Startup Genome's Top 100 Emerging Ecosystems, while also playing host to a number of multinational enterprises. In Calgary, job seekers can find a wide range of opportunities.
