Senior Inference Optimization Engineer - Dragonfly Portfolio
United States (Remote)
R
USD 152K-239K (estimate) Senior-level Full Time
Tasks
- Apply parallelism strategies for distributed inference
- Assess new inference hardware and accelerators
- Build GPU infrastructure and deployment
- Develop benchmarking harnesses for inference engines
- Evaluate and optimize quantization schemes
- Evaluate inference routing load balancing algorithms
- Implement continuous batching
- Manage KV cache and attention mechanisms
- Optimize LLM inference throughput
- Optimize TTFT and TPOT
- Profile GPU performance and optimize kernels
- Reduce latency and cost per token
Perks/Benefits
Skills/Tech-stack
ASICs | C++ | CUDA | CUDA Graphs | Continuous batching | Distributed inference | FPGAs | GPU Profiling | Go | HPC | KV cache | Mixture of Experts | Nsight Compute | Nsight Systems | PagedAttention | Parallel Programming | Pipeline parallelism | PyTorch | PyTorch Profiler | Python | Quantization | Rust | SGLang | Speculative decoding | Tensor Parallelism | Torch compile | Triton | VLLM
Education
N/A
Related jobs
-
Data Engineer CAD 100K-170KAWS | Apache Airflow | Azure | BigQuery | Cloud Computing401k | Asynchronous work culture | Autonomy | Company paid life insurance | Disability coverageMid-level Full TimeRemote - US or Canada R5h ago
-
Data Modeling & AI Analytics USD 133K-190KAirbyte | Amazon Redshift | BigQuery | DBT | Data GovernanceSenior-level Full TimeMiami, Florida R7h ago
-
Senior Research Engineer / Scientist - Storage for LLM USD 207K-368KCUDA | Caching | Data Structures | Distributed Systems | Eviction PolicyConference attendance | Open source contributions | Research resourcesSenior-level Full TimeSeattle, Washington, United States R8h ago
-
Research Engineer / Scientist - Storage for LLM USD 153K-300KCUDA | Caching | Distributed Systems | Eviction policies | GPU ComputingConference attendance | Innovation-driven culture | Open source contributions | Research resourcesEntry-level Full TimeSeattle, Washington, United States R8h ago
-
Software Engineer (Technical Leadership) USD 213K-293KC++ | Data Classification | Data Mining | Data Modeling | Data RegressionSenior-level Full TimeBellevue, WA | Menlo Park, CA … R9h ago
-
Data Engineer, Product Analytics USD 181K-204KAlgorithm Optimization | Bias Mitigation | C# | C++ | Data GovernanceCareer growth opportunitiesSenior-level Full TimeSunnyvale, CA | Bellevue, WA | … R9h ago
-
Senior Software Engineer - AI Interaction Evaluator (Codex / Claude Code, up to $200/hr) USD 200K-400KClaude Code | Cursor | JavaScript | OpenAI Codex | PythonSenior-level Full TimeMiami R18h ago
-
AI Security Engineer USD 140K-200K800-53 | ABAC | AI RMF | AI Studio | AKS401k matching | Dental insurance | Employee development program | Employee referral program | Medical insuranceSenior-level Full TimeRemote, MD, US R19h ago
-
Senior Middleware Software Development Engineer USD 128K-245KC# | C++ | Distributed Computing | GPU Software Development | GPU softwareHealth benefits | Hybrid work model | Retirement benefits | VacationSenior-level Full TimeUSA - OR - Hillsboro, United … R20h ago
-
Junior AI Engineer USD 86K-120KAPI Integration | Authentication | Cloud deployment | Docker | Error Handling401k matching | BYOD reimbursement | Company holidays | Flexible spending accounts | Health savings accountEntry-level Full TimeHouston, Texas, United States (Hybrid) R20h ago
-
AWS Bedrock | AWS Lambda | Amazon DynamoDB | Amazon S3 | Amazon SageMaker401k plan | Flexible time off | Global shutdown | Health insurance | Paid time offSenior-level Full TimePrinceton LVL - NJ, United States R20h ago
-
Staff Machine Learning Engineer, Traffic Intelligence USD 212K-265KBayesian Calibration | Bayesian Inference | Calibration | Causal Inference | Data PipelinesSenior-level Full TimeUnited States R21h ago
-
Senior Machine Learning Engineer USD 150K-241KC++ | Cloud Architecture | Computer Vision | Data Privacy | EncryptionDiscretionary paid time off | Emotional & mental wellness support | Employer 401k match | Fitness programs | Learning and development programsSenior-level Full TimeSeattle, Washington, United States R21h ago
-
Active Learning | Auto-labeling | Computer Vision | Confidence Scores | Data BalancingBonus program | Company benefits program | Equity incentive planSenior-level Full TimeMountain View, CA, USA; San Francisco, … R21h ago
-
Solution Engineer USD 165K-216KCloud Computing | Data Lake | Data Warehouse | Data fabric | Data meshTravelSenior-level Full TimeUS-OH-Remote R23h ago
-
Principal Data Engineer (Remote) USD 151K-189KAmazon Kinesis | Apache Spark | CI/CD | Cloud Data | Cloud Data Services12 weeks new parent leave | Coworking support | Flexible PTO | Learning & development stipend | Time allotment for learning and developmentSenior-level Full TimeUnited States R23h ago
-
Lead Data Engineer (Remote) USD 126K-157KAWS | AWS Redshift | Amazon Kinesis | Azure | Azure DataCoworking support | Flexible PTO | Learning and development stipend | New parent leave | Remote workSenior-level Full TimeUnited States R23h ago
-
Senior Machine Learning Engineer, Vehicle Perception USD 140K-230KAblation Studies | C plus plus | Cloud Computing | Computer Vision | Data CurationComprehensive benefits package | Hybrid work schedule | Incentive programsSenior-level Full TimePalo Alto, CA R23h ago
-
AWS | Agile | Azure | Azure Data | Azure Data FactoryHybrid work | Occasional onsite work | Onsite interviews as needed | Remote workSenior-level Full TimeUnited States R23h ago
-
AWS | Agile | Azure | Azure Data | Azure Data FactoryMid-level Full TimeUnited States R1d ago
-
Senior Analytics Engineer USD 141K-176KAWS Glue | Amazon Athena | Apache Hive | Apache Spark | CI/CDGenerous time off | Healthcare | Occasional travel for in person meetings | Paid personal time off | Paid sick timeSenior-level Full TimeRemote - US R1d ago
-
Embedded & Automation Engineer USD 140K-230KAbstraction layer | Bring up automation | Bring-up | C# | C++401k | Accident insurance | Critical illness insurance | DCFSA | Dental insuranceMid-level Full TimeSan Diego, CA R1d ago
-
Autonomous Systems | Build systems | C++ | Computer Vision | Core dumpsSenior-level Full TimeSunnyvale R1d ago
-
Senior Software Engineer (Forward Deployed) USD 180K-264KAWS | Automation | Data Contracts | Data Governance | Data QualityHybrid work | On-call support | Travel opportunitiesSenior-level Full TimeLondon - Hybrid; New York - … R1d ago
-
Data Scientist USD 90K-120KAWS | Agentic AI | Azure | Cypress | Data Analysis401k employer contribution | Remote work optionMid-level Full TimeRemote, USA R1d ago