Machine Learning Engineer — Inference Optimization
Tasks
- Benchmark model performance across hardware environments
- Build and maintain inference serving infrastructure
- Deploy and productionize new model architectures
- Implement quantization and KV cache optimization
- Implement speculative decoding batching and streaming
- Improve reliability monitoring and observability
- Optimize machine learning inference systems for latency throughput scalability and cost
- Profile and identify bottlenecks in GPU and CPU inference pipelines
Perks/Benefits
Skills/Tech-stack
Attention Mechanisms | CUDA | CUDA kernels | Cache optimization | Compute Graphs | Distributed Systems | GPU Performance | GPU Performance Optimization | KV cache | KV cache optimization | Long Context | Long context inference | Low Latency | Low-Latency Systems | Memory Optimization | Neural Networks | ONNX Runtime | Performance optimization | PyTorch | Quantization | ROCm | Speculative decoding | TensorRT | Triton | VLLM
Education
N/A
Related jobs
-
Data Engineer - AI/ML (f/m/d) GBP 50K-60KAWS | Agile | Azure | Azure Data | Azure Data FactoryFlexi-Week | Health and wellbeing support | Hybrid remote working | Peer to peer recognition voucher | Remote Working FurnitureMid-level Full TimeBerlin, Berlin, Germany; Iași, Iași, Romania; …19h ago
-
AI | Backend Development | Cluster management | Container Orchestration | Data EngineeringSenior-level Full TimeBucharest, Romania2d ago
-
API Design | Backend architecture | Command Line | Command-line Interface | Database systemsCompany equipment | Continuous learning allowance | Flexible working hours | Fully remote | Health insurance allowanceSenior-level Full TimeRomania R3d ago
-
AWS | Autoscaling | Bash | CI/CD | Data PipelinesFully remote work | Healthcare coverage | Paid parental leave | Relocation assistance | Technical ownershipMid-level Full TimeRomania R4d ago
-
APIs | AWS | Azure | CI/CD | GCPFlexible workingMid-level Full TimeBucharest - Dacia One, Romania4d ago
-
Algorithms | Concurrency | Data Structures | Database systems | Distributed SystemsFlexible schedule | Health insurance | Parental leave | Remote work | Service Donation MatchingSenior-level Full TimeRomania R4d ago
-
Algorithms | Concurrency | Data Structures | Database systems | Distributed SystemsDonation matching | Flexible schedule | Health coverage | Parental leave | Remote work flexibilitySenior-level Full TimeRomania R4d ago
-
Senior Python Engineer, DataFeed Team RON 295K-430KAPI Integration | APIs | Alerting | Apache Kafka | Asynchronous processingOn-call rotationSenior-level Contract Full TimeBucharest4d ago
-
AI Engineer RON 264K-396KAPI Architecture | AWS | Agent systems | Apache Spark | Azure25 vacation days | Focus Fridays | Generous leave package | Hybrid work | LinkedIn LearningSenior-level Full TimeBucharest, Bucharest, Romania R4d ago
-
Principal Data Engineer RON 264K-288KAmazon Web Services | Apache Spark | Azure | Azure Data | Azure Data FactoryAdditional annual leave based on tenure | Annual performance bonus | Employee referral bonus | Eyeglasses vouchers | Flexible working scheduleSenior-level Full TimeCluj, Romania5d ago
-
AI Engineer - L7R88V73 RON 197K-299KAWS | CI/CD | Computer Vision | Data Augmentation | Data DriftContinuous improvement culture | Continuous professional growth | Cross-functional collaboration | Inclusive workplace | Work-life balanceMid-level Full TimeBucharest, Romania7d ago
-
Auto Scaling | Blue-Green Deployment | Blue/green | CI/CD | CUDAFully remote | High ownership and influence | Remote work flexibilitySenior-level Full TimeRomania R8d ago
-
Senior-level Full TimeBrasov, RO9d ago
-
Senior Python AI Software Engineer (Contract, Romania) RON 279K-406KAgent systems | Agile | Autogen | Design Patterns | GitContract employment | Remote workSenior-level ContractRomania10d ago
-
Senior Backend Software Engineer(AI Teams) EUR 54K-79KAMQP | Amazon Web Services | CI/CD | ClickHouse | Database IndexingCareer development | Flexible working hours | Hybrid work | Remote workSenior-level Full TimeBerlin10d ago
-
Senior Embedded Linux Engineer RON 234K-290KC plus plus | C# | Device tree | Embedded Linux | Linux KernelFlexible benefits | Health insurance | Learning and development | Mental health resources | Wellness resourcesSenior-level Full TimeCluj-Napoca, Hexagon Office, Romania12d ago
-
Auto Scaling | CI/CD | CUDA | Container Orchestration | Distributed SystemsEnglish language support | On-call support | Remote workSenior-level Full TimeUkraine R14d ago
-
Mid-level Full TimeBrasov, RO15d ago
-
Cloud Data | Cloud Data Services | Data Services | MLOps | Machine LearningCertifications | Flexible or hybrid working | Learning budget | Meal tickets | Private medical careEntry-level Full TimeBucharest Orhideea, Romania16d ago
-
Senior Data Engineer Interviewer RON 296K-396KAWS Glue | Airflow | Amazon Web Services | Apache Spark | AuthenticationFlexible interview based schedule | Part-time workSenior-level Contract Full TimeRomania - Remote R19d ago
-
Machine Learning Engineer RON 173K-270KApache Airflow | Apache Arrow | Apache ELT | Apache ETL | Apache ParquetFlexible working | Health and wellbeing benefits | Hybrid work | Income protection | Life assuranceMid-level Full TimeRomania21d ago
-
AWS SageMaker | Amazon EMR | Amazon Redshift | Amazon S3 | Apache AirflowMid-level Full TimeBucharest, Romania22d ago
-
Senior Artificial Intelligence/Machine Learning Engineer RON 204K-278KAWS | Amazon SageMaker | Apache Beam | Azure | CI/CDMeal tickets | Medical subscription | Remote work optionSenior-level Full TimeRomania R22d ago
-
Senior AI Engineer (f/m/x) RON 312K-396KAI to AI | Agent systems | Agentic Workflows | Deep learning | Explainable AICoaching | Continuous learning culture | Flexible working hours | Hybrid work | Life insuranceSenior-level Full TimeBucharest, 6A Dimitrie Pompeiu Blvd, Romania24d ago
-
Amazon S3 | Argo CD | Argo Workflows | Azure | CI/CDMid-level Full TimeBucharest, RO25d ago