Machine Learning Engineer — Inference Optimization
Tasks
- Benchmark model performance across hardware
- Implement quantization and KV cache optimization
- Implement speculative decoding and batching
- Improve monitoring observability and reliability
- Optimize machine learning inference systems for latency and throughput
- Profile and identify GPU and CPU inference bottlenecks
- Reduce inference operational cost
- Serve and maintain model inference infrastructure
Perks/Benefits
Skills/Tech-stack
Attention Mechanisms | Batching | CUDA | Compute Graphs | Distributed Systems | GPU Performance | GPU Performance Optimization | KV cache | Machine Learning | Memory Optimization | Model Benchmarking | Network architectures | Neural Network | Neural Network Architectures | ONNX Runtime | Performance optimization | PyTorch | Quantization | ROCm | Speculative decoding | Streaming | TensorRT | Triton
Education
N/A
Related jobs
-
APIs | Attribution Modeling | Campaign Optimization | Causal Inference | ClusteringAccess to diverse client datasets | Collaborative team environment | Hybrid work model | Knowledge sharing | Opportunities for challenging projectsMid-level Contract FreelanceBrazil18h ago
-
Forward Deployed Engineer, Enterprise AI [LATAM] BRL 319K-396KAWS | Automated testing | Cloud Computing | Cloud platform | ComplianceSenior-level Full TimeSão Paulo, Brazil19h ago
-
Forward Deployed Engineer, Enterprise AI [LATAM] BRL 234K-295KAI | API Design | AWS | Cloud Computing | Cloud platformSenior-level Full TimeSão Paulo, Brazil19h ago
-
Adversarial Testing | Artificial Intelligence | Bias Assessment | Experiment tracking | Hallucination detectionContract based opportunity | Opportunity to work on advanced AI systems | Remote work flexibilitySenior-level Contract Full TimeBrazil R22h ago
-
Cloud infrastructure | Containerization | Docker | GPU Computing | KubernetesCareer growth in AI infrastructure | Four-day work week | Fully remote | Global team collaboration | Open communication inclusive cultureSenior-level Full TimeBrazil R22h ago
-
AMD GPU | BF16 | Backpropagation | Batch Size | Batch size tuningEquity opportunities | Fast feedback loops | High ownership | Opportunities for technical learningMid-level Full TimeBrazil23h ago
-
Deep learning | Distributed Training | GPU Training | JAX | Kernel optimizationAsync-first culture | High ownership role | Remote-friendly work environmentSenior-level Full TimeBrazil23h ago
-
AWS Textract | Autogen | Azure Form Recognizer | CI/CD | Computer VisionBirthday day off | Childcare assistance | Cultural partnerships | Dental insurance | Family support for new parentsSenior-level Full TimeBrazil R1d ago
-
Senior Data Engineer ID71670 BRL 300K-368KApache Airflow | Automated testing | Batch Processing | CI/CD | DagsterEducation budget | Exciting projects | Fitness budget | Flexible schedule | MentorshipSenior-level Full TimeCampinas, Brazil1d ago
-
Senior Data Engineer ID71670 BRL 300K-368KAWS | AWS Kinesis | Apache Airflow | Apache Kafka | AzureEducation budget | Fitness budget | Flextime | Mentorship | Office optionsSenior-level Full TimeFlorianópolis, Brazil1d ago
-
Agile | Azure | Azure Data | Azure Data Factory | Azure Data LakeCompany-sponsored certifications | Conference support | Continuing education | Flexible working hours | Paid time offSenior-level Full TimeManaus, Amazonas, Brazil R2d ago
-
Senior AI Engineer BRL 180K-271KAWS | Agentic AI | CI/CD | Computer Vision | Deep learningExtended paternity leave | Flexible career path | Flexible work hours | Hybrid work environment | Insurance planSenior-level Full TimeBR-CWB-002, Brazil2d ago
-
Engenheiro(a) de Dados | BigQuery & Airflow BRL 20K-27KApache Airflow | CI/CD | Change Data Capture | Cloud platform | Data CaptureBirthday off | Career mentoring | Childcare assistance | Company results participation | Dental insuranceSenior-level Full TimeSao Paulo, Torre Paineira, Brazil2d ago
-
Intermediate Machine Learning Engineer - Bees Data BRL 150K-220KAlerting | Azure Cloud | Azure DevOps | BentoML | CI/CDCasual office and dress code | Childcare subsidies | Days off | Dental insurance | Discounts on productsMid-level Full TimeCampinas, Brazil2d ago
-
Senior Machine Learning Engineer - Bees Data BRL 305K-390KAzure | Azure DevOps | BentoML | Databricks | Inference ServerCasual office and dress code | Childcare subsidies | Days off | Dental insurance | Discounts on Ambev productsSenior-level Full TimeCampinas, Brazil2d ago
-
AI Engineering I - Marketing USD 30K-39KAWS | BERT | CI/CD | Docker | EmbeddingsFull-time employment | Remote workEntry-level Full TimeBrazil, Remote R2d ago
-
Especialista I - Technical Lead BRL 210K-240KAWS | Acceptance Testing | Angular | Automation | CI/CDSenior-level Full TimeSão Paulo, SP, Brazil2d ago
-
Senior-level Full TimeSao Paulo, Brazil2d ago
-
AKS | Airflow | Azure | Azure Event | Azure Event HubsChildcare support | Commuter Transit Benefits | Dental plan | Employee benefits club | Flexible parental leaveMid-level Full TimeSão Paulo, SP2d ago
-
API documentation | Airflow | Amazon Web Services | Apache Beam | Apache SparkBirthday day off | Dental insurance | Educational support programs | Fitness and wellness partnerships | Fully remote workMid-level Full TimeBrazil R3d ago
-
Azure | Data Quality | Databricks | Fraud Detection | MLOpsChildcare assistance | Dental insurance | Gym membership | Health insurance | Life insuranceEntry-level Full TimeOSASCO, Brazil; CURITIBA, PR, Brazil; OSASCO, …3d ago
-
Data Engineer III BRL 18K-18KDatabricks | MLOps | Machine Learning | PySpark | PythonChildcare assistance | Dental insurance | Food and meal allowance | Health insurance | Life insuranceSenior-level Full TimeOSASCO, Brazil; CURITIBA, PR, Brazil; OSASCO, …3d ago
-
.NET | AI Search | AWS | Agent systems | AgileRemote workSenior-level Full TimeAlphaville - Barueri, BR, 06.454-0003d ago
-
AI Engineer II - Marketing USD 39K-72KAWS | CI/CD | Docker | Entity recognition | Feature EngineeringFull-time employment | Remote workMid-level Full TimeBrazil, Remote R3d ago
-
Data Engineer USD 120K-147KAWS | Apache Airflow | Apache Spark | Azure | Batch ProcessingFully remote | Professional growth opportunitiesMid-level Full TimeBrazil R3d ago