AI Research Engineer (Model Compression & Quantization)
Tasks
- Address production inference bottlenecks
- Analyze efficiency accuracy trade offs across compression methods
- Apply low-bit quantization to reduce model size and inference latency
- Build compression pipelines for multimodal architectures
- Document experiments and publish reproducible results
- Establish performance and fidelity metrics for compressed models
- Implement pruning to reduce redundant parameters and attention heads
- Leverage knowledge distillation to train smaller multimodal models
- Publish technical papers in top conferences
- Research mixed precision quantization to optimize accuracy performance balance
Perks/Benefits
Skills/Tech-stack
Backpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed Precision | Model Pruning | Neural Network | Optimization | Post-training | Post-training Quantization | PyTorch | Quantization | Quantization aware training | Transformer
Education
Roles
Related jobs
-
AI Research Engineer GBP 110K-200KC# | CUDA | Deep learning | Machine Learning | PyTorchHybrid Remote | Remote Interview AccommodationMid-level Full TimeHybrid (UK) R3h ago
-
Cloud Computing | Data Pipelines | ETL | Google Colab | Information RetrievalCareer growth opportunities | Continuous learning culture | Coworking access | Flexible schedule | Fully remote workMid-level Full TimeIreland R5h ago
-
AI Research Engineer - Applied AI INR 2000K-3000KAPI Design | AWS SageMaker | Anomaly Detection | Azure Machine Learning | Bias auditingAsynchronous culture | Distributed team | Remote workMid-level Full TimeRemote - REMOTE, India, India R10h ago
-
Senior Machine Learning Engineer, Model Training & Evaluation INR 2500K-4500KBenchmarking | Checkpointing | DeepSpeed | Distributed Training | Experiment trackingAccidental insurance | Flexible hours | Hybrid work | Life insurance | Medical insuranceSenior-level Full TimeBangalore, India (Hybrid) R11h ago
-
Senior Software Engineer USD 140K-185KAWS | Automated testing | Azure | C++ | Git401K company matching | Dental insurance | Dependent care benefits | Flexible spending account | Health insuranceSenior-level Full TimeBoulder, CO R15h ago
-
Compute Shaders | Diffusion Models | Distributed inference | Edge Computing | Expert parallelism100 percent remoteSenior-level Full TimeRemote job R17h ago
-
AI Research Engineer (Model Compression & Quantization) USD 206K-327KBackpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed PrecisionRemote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Kernel & Inference Optimization) USD 201K-332KComputer Vision | Diffusion Models | Edge Computing | Expert parallelism | Flash AttentionRemote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Model Compression & Quantization) USD 206K-327KBackpropagation | Finetuning | GenerativeAI | KnowledgeDistillation | MixedPrecisionRemote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Model Compression & Quantization) USD 206K-327KBackpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed PrecisionRemote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Model Compression & Quantization) USD 206K-327KBackpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed PrecisionEnglish communication requirement | Remote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Kernel & Inference Optimization) USD 201K-332KCompute Shaders | Diffusion Models | Distributed inference | Edge Computing | Expert parallelismEnglish communication support | Remote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Model Compression & Quantization) USD 206K-327KBackpropagation | C++ | Knowledge Distillation | Mixed Precision | Model PruningFlexible collaboration | Remote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Model Compression & Quantization) USD 210K-330KBackpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed PrecisionRemote workSenior-level Full TimeRemote job R18h ago
-
AI Research Engineer (Model Compression & Quantization) USD 210K-330KBackpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed PrecisionEnglish communication support | Remote workSenior-level Full TimeRemote job R18h ago
-
Senior AI Engineer - RAG & AI Agents EUR 56K-82KAI Agents | AWS | CI/CD | ChromaDB | CouchbaseAnnual learning budget | Equipment budget | Fitness subscription | Flexible hours | Health insuranceSenior-level Full TimeRemote R18h ago
-
Machine Learning Engineer USD 150K-215KData Augmentation | Deep learning | Isaac | Loss Functions | Medical ImagingMid-level Full TimeSan Francisco (hybrid) R19h ago
-
AI Research Engineer (Model Compression & Quantization) USD 210K-330KBackpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed PrecisionRemote work flexibility | Research publication supportSenior-level Full TimeRemote job R20h ago
-
AI Research Engineer (Model Compression & Quantization) USD 210K-330KBackpropagation | C++ | Fine Tuning | Knowledge Distillation | Mixed PrecisionRemote workSenior-level Full TimeRemote job R20h ago
-
AI Research Engineer (Kernel & Inference Optimization) USD 201K-332KDiffusion Models | Distributed Inference Systems | Distributed inference | Edge Computing | Expert parallelismRemote workSenior-level Full TimeRemote job R20h ago
-
Diffusion Models | Distributed Inference Systems | Distributed inference | Expert parallelism | Flash Attention100 percent remote | Worldwide remoteSenior-level Full TimeRemote job R20h ago
-
Mid-level Full TimeSlovenia / Remote R22h ago
-
Benchmarking | Data Balancing | Data Filtering | Dataset curation | Distributed TrainingRemote work worldwideSenior-level Full TimeRemote job R22h ago
-
Audio Processing | Autoregression | Autoregressive models | Computer Vision | Deep learningRemote workSenior-level Full TimeRemote job R22h ago
-
AI Scientist DKK 499K-734KApache Spark | Azure | Databricks | Deep learning | Delta LakeBusiness resource groups | Charitable donation stipend | Flexible work hours | Health stipend | Paid time offMid-level Full TimeCopenhagen R23h ago