Optimize and compress large language and vision models for on-device inference. Develop distillation and hardware-specific compilation pipelines, deploy models to edge devices, and benchmark performance across NPU/GPU architectures to ensure efficient on-device operation.
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
Artificial Intelligence • Information Technology • Professional Services • Consulting
Debug and improve diverse codebases by fixing software defects, identifying vulnerabilities, conducting security assessments, refactoring legacy code, and optimizing secure backend systems. The specialist will document technical findings and contribute cybersecurity and software engineering expertise to AI training datasets. Work is fully remote and requires independent execution across project specifications.
Top Skills:
C++GoJavaPython 3RustTypescript
Agency • Artificial Intelligence • Blockchain • Web3
Perform adversarial testing and red-teaming on large language and multimodal models, implement runtime guardrails and filtering, and help develop constitutional AI principles and RLHF alignment pipelines to ensure safe AI deployment.
Top Skills:
Adversarial MlConstitutional AiJailbreak TaxonomiesLlmsMultimodal AgentsPrompt EngineeringRed-Teaming FrameworksRlhf
Cloud • Computer Vision • Information Technology • Sales • Security • Cybersecurity
Lead complex cybersecurity investigations across endpoint, identity, email, network, and cloud environments. Analyze EDR telemetry, forensic artifacts, network data, malware, and Microsoft 365 attacks to determine root cause and scope. Develop remediation plans, mentor analysts, improve SOC processes, build automation, and advise customers during critical incidents. Contribute to threat intelligence, detection strategy, AI-enabled security operations, thought leadership, and industry engagement.
Top Skills:
Agentic Soc WorkflowsAi ModelsEdrMicrosoft 365Mitre Att&CkPrompt Engineering
What you need to know about the Sydney Tech Scene
From opera to comedy shows, the Sydney Opera House hosts more than 1,600 performances a year, yet its entertainment sector isn't the only one taking center stage. The city's tech sector has earned a reputation as one of the fastest-growing in the region. More specifically, its IT sector stands out as the country's third-largest, growing at twice the rate of overall employment in the past decade as businesses continue to digitize their operations to stay competitive.
