Applied AI Engineer, Inference
Bellevue, WA/ San Francisco, CA/ Sunnyvale, CA
USD 188K-275K Mid-level Full Time
Tasks
- Benchmark inference stack against customer workloads
- Build benchmarking workflows
- Create technical writeups and recommendations
- Design experiments for quantization and speculative decoding
- Drive targeted inference optimizations
- Identify performance bottlenecks
- Measure latency throughput quality regressions cost
- Productionize performance improvements
- Profile model serving behavior
- Tune serving configurations
- Validate changes against benchmarks and traces
Perks/Benefits
- 401k employer match
- Disability insurance
- Employee stock purchase program
- Flexible PTO
- Flexible spending account
- Health savings account
- Life insurance
- Medical, dental, and vision insurance
- Mental wellness benefits
- Paid parental leave
- Tuition reimbursement
Skills/Tech-stack
Batching | Benchmarking | CUDA | GPU Utilization | Graph Capture | Inference Optimization | KV cache | Latency optimization | Machine Learning | Model Serving | Nsight Systems | Profiling | PyTorch | Python | Quantization | SGLang | Speculative decoding | TensorRT-LLM | Throughput Optimization | VLLM
Education
N/A
Roles
Regions
Countries
States
Related jobs
-
Featured Feat. Principal Knowledge & Data Architect USD 174K-284KAWS Neptune | Canonicalization | Chunking | Cypher | DBTBenefits including health and wellness programs | Health, wellness, and retirement plansSenior-level Full TimeHeadquarters - Chevy Chase, MD R22d ago
-
Principal AI Engineer (Remote) USD 128K-200KAPI Gateways | Agent Orchestration | Artificial Intelligence | BigQuery | By DesignAfter hours incident support | Occasional overtime | Occasional travel | Remote workSenior-level Full TimeOak Brook, IL, United States R2h ago
-
Infrastructure Engineer USD 180K-250KAWS | Azure | Docker | GCP | GPU ComputingOnsite in SF Bay Area | Relocation supportEntry-level Full TimeSan Francisco, CA, US4h ago
-
APIs | AWS | Agentic AI | Azure | Claude401k | Dental insurance | Fully remote US based | Generous PTO | HolidaysSenior-level Full TimeRemote USA, United States R4h ago
-
Staff Data Engineer USD 190K-250KAWS | Agent systems | Airflow | Alation | Amazon KinesisDental insurance | Flexible working hours | Health insurance | Hybrid options | Learning resourcesSenior-level Full TimeDallas, TX, United States4h ago
-
.NET | ArgoCD | Automation | Bash | C#Mid-level Full TimeDallas, Texas, United States; Hermitage, Tennessee, …5h ago
-
AI & Machine Learning Engineer USD 98K-140KAmazon Web Services | Apache Kafka | Azure | C++ | CI/CD401k match | Company paid life insurance | Medical, dental, and vision insurance | Paid Holidays | Paid time offMid-level Full TimeUSA-WISCONSIN-Green Bay5h ago
-
Data Engineer, Technical Leadership (Ranking, AI) USD 182K-235KAI workflows | Data Architecture | Data Governance | Data Modeling | Data QualitySenior-level Full TimeMenlo Park, CA7h ago
-
Software Engineer, SystemML - AI Networking USD 170K-287KC# | C++ | CUDA | Data-parallel | Distributed Data ParallelMid-level Full TimeMenlo Park, CA7h ago
-
Senior Performance Co-Design Engineer, LLM Serving USD 174K-252KC++ | Co-design | Computer Architecture | Deep learning | Deep learning inferenceSenior-level Full TimeSunnyvale, CA, USA7h ago
-
Staff Software Engineer, YouTube Ads Machine Learning USD 207K-300KData Processing | Data Storage | Distributed Computing | Embeddings | Fine TuningBonus | Equity | Health insurance | Paid time off | Retirement plansSenior-level Full TimeMountain View, CA, USA7h ago
-
Data Structures | Data Structures and Algorithms | Distributed query | Distributed query processing | Linux KernelSenior-level Full TimeMountain View, CA, USA; Zürich, Switzerland7h ago
-
Automated testing | C# | C++ | CI/CD | Continuous DeploymentMid-level Full TimeMountain View, CA, USA7h ago
-
Data Processing | Debugging | Distributed Computing | Information Retrieval | Language ModelsSenior-level Full TimeSunnyvale, CA, USA7h ago
-
C++ | Data Processing | Debugging | Generative AI | Google CloudHealth insurance | Learning and development opportunities | Paid time off | Relocation assistance | Retirement planSenior-level Full TimeMountain View, CA, USA7h ago
-
C++ | Data Processing | Debugging | Language Models | Language ProcessingSenior-level Full TimeMountain View, CA, USA7h ago
-
Senior Software Engineer, AI/ML GenAI, Google Workspace USD 174K-252KAlgorithms | C++ | Data Processing | Data Structures | DebuggingSenior-level Full TimeSunnyvale, CA, USA7h ago
-
Senior Software Engineer, Google Cloud Storage USD 174K-252KAlgorithms | C# | C++ | Cloud Computing | Data IntegritySenior-level Full TimeNew York, NY, USA7h ago
-
Software Engineer III, AI/ML, AI and Infrastructure USD 147K-210KAlgorithms | C++ | Data Processing | Data Structures | DebuggingSenior-level Full TimeSunnyvale, CA, USA7h ago
-
Senior Performance Co-design Engineer, LLM Training USD 174K-252KC++ | Co-design | Computer Architecture | Data parallelism | Distributed TrainingSenior-level Full TimeSunnyvale, CA, USA7h ago
-
Artificial Intelligence | C++ | Cloud Security | Cybersecurity | Data ProcessingSenior-level Full TimeSunnyvale, CA, USA; Kirkland, WA, USA7h ago
-
Senior Software Engineer, Generative AI, Google Meet USD 174K-252KComputer Vision | Data Processing | Debugging | Distributed Computing | Language ModelsSenior-level Full TimeRaleigh, NC, USA; Durham, NC, USA7h ago
-
Data Engineer - Emergency Preparedness and Response USD 117K-151KAzure | Azure Data | Azure Data Factory | Azure Databricks | Big DataEmergency response availability | Health safety wellbeing focus | Hybrid work scheduleMid-level Full TimeDetroit, MI, US11h ago
-
Software Engineer, Embedded Agentic AI USD 170K-210KAgent Orchestration | Agent systems | C# | C++ | Cloud PlatformsDisability benefits | Equity awards | Health insurance | Life insurance | Paid time offEntry-level Full TimeSan Jose, California14h ago
-
Staff Engineer, GenAI Tooling & DevEx (R5469) USD 121K-197K*nix | AWS | Access Management | Active Directory | Azure GovSenior-level Full TimeWashington, DC16h ago