Member of Technical Staff - Inference Research
Tasks
- Build autoscaling for serverless traffic
- Collaborate with research labs
- Deploy and tune models with customers
- Design disaggregated prefill decode
- Develop speculative decoding
- Implement quantization strategies
- Improve observability for latency and quality
- Manage KV cache and memory
- Own end to end inference research bets
- Train and evaluate custom speculators
- Turn serving research into product primitives
Perks/Benefits
Skills/Tech-stack
Autoscaling | Disaggregated Prefill | FP8 | INT4) | KV cache | Kernels | LLM Inference | Language Models | Large Language Models | Memory Management | Model Deployment | Model Serving | Observability | Quantization | Speculative decoding | Tail Latency
Education
N/A
Regions
Countries
States
Related jobs
-
Featured Feat. Associate Director, Data Labs USD 167K-167KAWS | Cloud Computing | Compute Infrastructure | Data Analysis | LLM GovernanceConference speaking opportunities | Hybrid work schedule | Media appearancesSenior-level Full TimeWashington, District of Columbia, 20004, United … R9d ago
-
Business Analysis | Customer Requirements | Data Modeling | Language Models | Language ProcessingHealth insurance | Mentorship | Paid time offMid-level Full TimeNew York, US, New York9h ago
-
API Development | AWS | Amazon SageMaker | Automated testing | CI/CDFlexible work arrangements | Health, dental, vision coverage | Hybrid work arrangement | Innovation opportunities | Internal mobilitySenior-level Full TimeCanada15h ago
-
BI tools | CI/CD | Data Modeling | Data Quality | Data WarehousingCareer growth | Flexible work arrangement | Greenfield project ownership | Occasional travel | Opportunity for diverse client engagementsMid-level Full TimeCanada15h ago
-
Member of Technical Staff - Post-Training Research USD 150K-350KDeep learning | Distributed Training | Knowledge Distillation | Language Models | Language ProcessingIn-person work optionSenior-level Full TimeNew York17h ago
-
AI/Machine Learning Engineer USD 130K-177KAWS | Apache Spark | Azure AI | Azure Machine Learning | DatabricksMid-level Full TimeCarmel, Indiana- Hybrid OR St. Louis, … R1d ago
-
Robotics Software Engineer USD 155K-300KC++ | Device Drivers | EBPF | GPU Profiling | Kernel programmingSenior-level Full TimeSan Francisco1d ago
-
Staff AI engineer USD 170K-250KAI Model Evaluation | AI model | AWS | Agent Orchestration | CachingFlexible working hours | Hybrid work culture | Unlimited time offSenior-level Full TimeSan Francisco1d ago
-
APIs | Distributed Systems | Fine Tuning | Human-in-the-loop | JavaScriptFlexible Remote Or Hybrid Work Within Canada | Health, dental, vision coverage | Learning and development supportSenior-level Full TimeCanada2d ago
-
API Design | Agent Frameworks | Cloud infrastructure | Distributed Systems | Evaluation PipelinesDental insurance | Health insurance | Professional growth opportunities | Remote-first work environment | Stock optionsSenior-level Full TimeCanada2d ago
-
Data Engineer USD 90K-110KAWS | AWS Lambda | Amazon DynamoDB | Amazon EMR | Amazon RedshiftFlexible schedule for time zone overlap | Remote workMid-level ContractNew York, NY R2d ago
-
Research Engineer, Inference USD 250K-325KAnalog computing | Attention | C++ | Efficient Attention | In-Memory ComputingMid-level Full TimeNew York City2d ago
-
Research Engineer, Life Sciences USD 350K-500KCloud deployment | Containerization | Data Pipelines | Docker | KubernetesFlexible work policy | Flexible working hours | Optional equity donation matching | Parental leave | Vacation leaveSenior-level Full TimeSan Francisco, CA2d ago
-
Mid-level Full TimeChicago3d ago
-
Senior Lead Software Engineer - Python/AWS/AI/LLM USD 175K-195KAWS | Algorithms | Anthropic | Artificial Intelligence | Data MiningBackup childcare | Financial coaching | Health care coverage | Mental health support | On-site wellness centersSenior-level Full TimeJersey City, NJ, United States3d ago
-
Agent Orchestration | Context engineering | Data Pipelines | Deployment Automation | Developer ToolingDirect path from idea to ship | High ownership | Mentorship opportunities | Startup-like environmentSenior-level Full TimeMenlo Park, CA3d ago
-
A/B Testing | B testing | Data Processing | Experimentation | Feature EngineeringHigh ownership | Mentorship | Short path from idea to shipSenior-level Full TimeMenlo Park, CA3d ago
-
Embedding retrieval | Experimentation | Information Retrieval | Large-Scale Search | Large-scaleHigh ownership | Opportunity to shape product | Short path from idea to shipSenior-level Full TimeMenlo Park, CA3d ago
-
APIs | Artificial Intelligence | C++ | Cloud infrastructure | Code readingSenior-level Full TimeNew York, NY, USA; Austin, TX, …3d ago
-
Software Engineer, GDC LLM Serving and GPU Performance USD 207K-301KBenchmarking | Data Processing | Debugging | Distributed Computing | Fine TuningSenior-level Full TimeSunnyvale, CA, USA; Seattle, WA, USA3d ago
-
AI Safety | Alignment | Artificial Intelligence | Cybersecurity | Data MiningMid-level Full TimeSan Francisco, CA, USA; London, UK3d ago
-
ABAC | AWS Bedrock | AWS Glue | AWS S3 | Amazon RedshiftEquity or stock options | Health dental and wellness benefits | Professional development opportunities | Remote first within CanadaSenior-level Full TimeCanada3d ago
-
Amazon Web Services | C++ | CUDA | Cloud platform | Deep learningFlexible work arrangements | Fully remoteMid-level Full TimeCanada R3d ago
-
Amazon Web Services | Argo CD | Argo Workflows | Bash | CI/CDEquity opportunities | Family support benefits | Flexible work arrangements | Health, dental, vision coverage | Learning and development supportSenior-level Full TimeCanada R3d ago
-
AI Foundry | AWS Bedrock | Agent Frameworks | Agent Orchestration | AnthropicMid-level Full TimeHouston, TX, United States R3d ago