Senior ML Engineer - Kimchi (LLM Inference Optimization)
Tasks
- Design benchmarking and optimization direction
- Implement quantization schemes
- Improve KV cache utilization
- Optimize LLM inference throughput
- Profile inference bottlenecks
- Reduce LLM latency
- Reduce model cold start time
- Scale distributed inference across nodes
Perks/Benefits
- Conference access
- Equipment budget
- Equity options
- Extra days off
- Flexible work hours
- Hackathon
- Learning budget
- Remote-first
- Team-building budget
Skills/Tech-stack
AWS | Argo CD | ArgoCD | Azure | CUDA | CUDA profiling | ClickHouse | Cloud Pub/Sub | Collective communication | Continuous batching | Distributed Systems | FP8 | GCP | GCP Pub/Sub | GitLab | GitLab CI | Grafana | INT4) | INT8 | KV cache | Kubernetes | Loki | Multi-GPU | Multi-node | Paged Attention | PostgreSQL | Prometheus | Pub/Sub | PyTorch | Python | Quantization | SGLang | Sharding | Speculative decoding | Tempo | TensorRT-LLM | VLLM
Education
N/A
Related jobs
-
Data Engineer Azure – Digital Factory (H/F) EUR 42K-47KAzure | Azure Container | Azure Container Instances | Azure Data | Azure Data LakeTeleworkEntry-level Full TimeNeuilly-sur-Seine, IDF, France R13h ago
-
Apache Spark | Azure | CI/CD | Data Quality | DatabricksCitizenship engagement platform | Employee representative council | Health insurance | Meal vouchers | Profit sharingSenior-level Full TimeNantes, Pays de la Loire, France R1d ago
-
Experienced Data Engineer - Streaming Platform EUR 55K-80KAWS Kinesis | Amazon Kinesis | Apache Flink | Apache Kafka | Apache PulsarChild day care | Gym membership | Lunch vouchers | Premium healthcare | Relocation assistanceMid-level Full TimeParis R2d ago
-
Data Engineer GCP (F/H) EUR 50K-55KAPI Development | Agile | BigQuery | CI/CD | Cloud BuildCareer development | Learning platform access | Remote work | Supportive managementMid-level Full TimeParis, Île-de-France, France R2d ago
-
Data Engineer AWS (F/H) EUR 30K-42KAWS Glue | AWS Lambda | Amazon Athena | Amazon S3 | Amazon Web ServicesELearning access | English courses | Health insurance | Mobility allowance | RTTSenior-level Full TimeLa Garenne-Colombes, Île-de-France, France R2d ago
-
Data Engineer EUR 50K-55KAPI | Agile | Apache Spark | Hadoop | KafkaE-learning access | English courses | Health insurance | Hybrid remote work | Meal ticketsMid-level Full TimeSophia-Antipolis, Provence-Alpes-Côte d'Azur, France R2d ago
-
Data Engineer AWS Senior (F/H) EUR 30K-42KAPI Gateway | AWS | Agile | Amazon Cognito | CI/CD100 percent health insurance coverage | Cooptation bonus | ELearning access | English courses | Health insuranceSenior-level Full TimeLa Défense, Île-de-France, France R2d ago
-
Data Engineer Cloud (F/H) EUR 30K-42KAWS | AWS Glue | AWS Lambda | AWS Step Functions | AgileAccord télétravail | Accès plateforme e-learning | Avantages CE | Cours anglais interne | Formation certifications techniquesSenior-level Full TimeLa Défense, Île-de-France, France R2d ago
-
Data Engineer GCP Senior (F/H) EUR 30K-42KBash | Cloud platform | Docker | GCP | GitCE benefits | Cooptation bonus | Employee benefits | English classes | Health insuranceSenior-level Full TimeLa Défense, Île-de-France, France R2d ago
-
Data Engineer H/F EUR 52K-57KArtifactory | Cloudera | ELK | Git | GrafanaEAP benefits | Health insurance coverage | Meal tickets | Mobility bonus | Referral bonusExecutive-level Full TimeParis, Île-de-France, France R2d ago
-
Freelance Machine Learning Engineer USD 116KLangchain | MLOps | Machine Learning | NumPy | PandasPart time freelance projects | Project based workMid-level FreelanceFrance - Remote R2d ago
-
Deep learning | Generative AI | LLMs | Langchain | MLOpsProject based workMid-level FreelanceFrance - Remote R2d ago
-
Data Engineer Azure – Digital Factory (H/F) EUR 42K-47KAgile | Alerting | Azure | Azure Container | Azure Container InstancesGreat Place to Work certifications | Health and wellbeing support N/A | Long-term mission | Telework 2 days per weekEntry-level Full TimeNeuilly-sur-Seine, IDF, France R4d ago
-
AWS | Amazon S3 | Apache Airflow | CI/CD | DBTCareer international opportunities | Equipment provided | Remote work 2 days per week | Training and certificationsMid-level Full TimeLille - Btwin Village, Nord, France R4d ago
-
Bash | Coverage.py | Dagger | Docker | GcovFlexible hours | Freelance project-based collaboration | Fully remote | Supportive global communitySenior-level Full TimeFrance - Remote R4d ago
-
Feature Engineering | LLMs | Langchain | MLOps | Machine LearningFreelance opportunities | Part-time engagement | Project based workMid-level FreelanceFrance - Remote R4d ago
-
GenAI Engineer (F/H) - Rennes EUR 46K-48KAPIs | Agents | Cloud platform | Docker | EvaluationAccess to internal institute | Hybrid work | Meetups and labs | Training programs | Weekly tech eventsEntry-level Full TimeRennes R5d ago
-
Developpeur Python Data science (F/H) EUR 42K-50KAngular | CI/CD | Langchain | Pandas | Prompt engineeringFlexible telework | Meal tickets | Paid time off | RTT | Training opportunitiesSenior-level Full TimeNantes, Pays de la Loire, France R5d ago
-
GenAI Engineer (F/H) - Nantes EUR 45K-48KAPIs | Cloud Native | Cloud platform | Docker | FastAPIAccess to SFEIR Institute | Conference access | Internal trainings | Meetups and labs | Technical communityEntry-level Full TimeNantes R5d ago
-
API platforms | Access Control | Alerting | Automation | CI/CDPaid leave | RTT days | Telework availableSenior-level ContractEurope, France, Ile-de-France, Hauts-de-Seine (92) R5d ago
-
Apache Hadoop | Apache Hive | Apache Kafka | Apache Spark | Azure HDInsightCSE benefits | Career growth opportunities | Community volunteering platform | Conference access | Employee representative bodySenior-level Full TimeNantes, Pays de la Loire, France R5d ago
-
Deep learning | Distributed Training | Evaluation protocols | Experimentation Frameworks | Exploration Exploitation TradeoffAutonomy | Fully remote | Global First Work Environment | Innovation culture | Research publication supportMid-level Full TimeFrance R5d ago
-
AWS Lambda | AWS Secrets | AWS Secrets Manager | Airflow | Amazon CloudWatchCollaborative team culture | Continuous learning and professional development | Flexible working hours | Fully remote across Europe | Ownership driven engineering cultureMid-level Full TimeFrance R5d ago
-
Senior Data Engineer | Apache NiFi EUR 65K-87KAPIs | AWS | Amazon Redshift | Apache Kafka | Apache NiFiAnnual leave | Flexible benefits plan | Meal allowance | Private medical insuranceSenior-level Full TimeFrance, France R6d ago
-
API Integration | API Keys | Apache Airflow | Authentication | Automated testingAutonomy | Continuous improvement | Exposure to production greenfield platform | Flexible collaboration hours | Fully remote work Europe UKSenior-level Full TimeFrance R6d ago