AI Performance Optimization Engineer
Tasks
- Advise on hardware and software adoption
- Build benchmark suites and regression frameworks
- Document performance tuning playbooks
- Drive compiler level optimization for model performance
- Identify and eliminate performance bottlenecks
- Implement and tune quantization sparsity and pruning
- Optimize AI training and inference pipelines for throughput latency and cost
- Optimize KV cache and batching for LLM serving
- Optimize data pipelines and storage access patterns
- Optimize distributed training parallelism and sharding
- Profile and measure CPU GPU and distributed systems
- Stay current with AI systems research
- Tune attention implementations
Perks/Benefits
- N/A
Skills/Tech-stack
Benchmarking | C++ | Cache optimization | Compiler optimization | Continuous batching | Data Sharding | Deep learning | Distributed Training | FSDP | FlashAttention | GPU Architecture | KV cache | KV cache optimization | Memory Management | Model Parallelism | Paged Attention | Parallelism Strategies | Pipeline parallelism | Profiling | Pruning | Python | Quantization | Sparsity | Speculative decoding | Storage Access | TVM | Tensor Parallelism | TorchInductor | Triton | XLA | Zero
Education
Related jobs
-
Senior-level Full TimeUnited States R17h ago
-
Deep Learning Quality Specialist USD 72K-90KAnnotation Guidelines | Computer Vision | Confluence | Convolutional Neural Networks | Data Annotation401k plan | Commuter benefits | Employee assistance program | Flexible PTO | Fully paid medical/dental/visionMid-level Full TimeSeattle, WA R23h ago
-
Corporate AI Engineer USD 154K-200KAPI Integration | Access Control | Data Quality | Embeddings | Generative AIHybrid work schedule | Volunteer time offMid-level Full TimeAddison, TX (Hybrid); Bellevue, WA (Hybrid); … R23h ago
-
Agile | Amazon RDS | Amazon S3 | Jira | MongoDBPST time zone requirement | Remote workMid-level Full Timeremote, CA R1d ago
-
AI Observability | AWS | Azure | CI/CD | Cost ControlCareer advancement | Fully remote work | Professional development opportunities | Work-life balanceSenior-level Full TimeCanada R1d ago
-
Senior Data Engineer 🇺🇸 USD 160K-200KAWS Glue | AWS Redshift | Amazon S3 | Apache Spark | Automated testingSenior-level Full TimeHybrid (New York, New York, US) R1d ago
-
AWS Data Engineer - Fully Remote - US Only USD 139K-210KAWS Glue | AWS Lambda | AWS Step Functions | Amazon DynamoDB | Amazon RedshiftAbility to work independently | Fully remote | US onlySenior-level Full TimePlano, Texas, United States - Remote R1d ago
-
AI Workflow Orchestration | AI workflow | AWS DynamoDB | AWS Lambda | AWS Step FunctionsArchitectural influence | Engineering Led Collaboration | High technical ownership | Learning opportunities | Remote-first work modelSenior-level Full TimeCanada R1d ago
-
Sr. AI Engineer USD 150K-175KAccess Control | Agentic Frameworks | Auditability | CI/CD | Cloud Native401-k match | Dental insurance | Expense Reimbursement for Home Office | Life insurance | Medical insuranceSenior-level Full TimeRemote, USA, United States R1d ago
-
Senior Analytics Engineer USD 159K-200KAWS | Airflow | DBT | Dagster | Data ObservabilityAutonomy | Fully remote | High-impact work | Use of AI toolsSenior-level Full TimeRemote US R1d ago
-
Senior-level Full TimeSan Jose, United States R1d ago
-
Lead Data Engineer USD 188K-230KAirflow | Apache Spark | Azure Cosmos | Azure Cosmos DB | Azure DataDomestic travel up to 5 percent | Relocation not authorized | Remote workSenior-level Full TimeRemote - Minnesota, United States R1d ago
-
BigQuery | Cloud Data | Cloud data platform | Code review | DBTLong-term contract | Onsite work in Atlanta GA metro area | Potential conversion to full time | W2 employmentSenior-level Contract Full TimeAtlanta, Georgia, United States R1d ago
-
Computational statistics | MATLAB | NumPy | Pandas | PythonPart-time freelance | Project based workSenior-level FreelanceNew York, New York, United States … R1d ago
-
Combinatorics | Graph theory | Mathematical Statistics | NumPy | Number theoryFlexible hours | Paid per project | Part-time freelance work | Project based workSenior-level FreelanceTexas, United States - Remote R1d ago
-
MATLAB | NumPy | Pandas | Python | RFlexible scheduling | Part-time project-based workSenior-level FreelanceFlorida, United States - Remote R1d ago
-
C# | MATLAB | NumPy | Pandas | PythonPart-time schedule | Project based workSenior-level FreelanceMichigan, United States - Remote R1d ago
-
MATLAB | NumPy | Pandas | Python | RFlexible schedule | Part-time hours | Project based workSenior-level FreelanceUnited States - Remote R1d ago
-
AI Data Infrastructure Engineer USD 100K-150KApache Beam | CI/CD | Caching | Code review | CompressionCareer growthMid-level Full TimeUnited States - Remote R1d ago
-
Staff Machine Learning Engineer, Adobe Firefly Services USD 172K-306KAdversarial Networks | CUDA | Diffusion Models | Distributed Systems | GANsSenior-level Full TimeSeattle, United States R1d ago
-
Finance Data Analyst- Analytics & AI USD 106K-129KAI | ARR | Anomaly Detection | Churn | Conversational AnalyticsMid-level Full TimeRemote - Maine, United States R1d ago
-
AI Engineer USD 89K-138KAWS | Agile | Automation | Compliance | Data SecurityDisability benefits | Health insurance | Life insurance | Paid time off | Retirement planSenior-level Full TimeRemote - CO, United States R1d ago
-
Senior Machine Learning Operations Engineer USD 166K-208KAlerting | CI/CD | Canary Deployment | Champion Challenger | Drift DetectionSenior-level Full TimeSan Francisco, CA, New York, NY, … R1d ago
-
AI Engineer USD 99K-163KAPI Integration | AWS | Amazon Bedrock | Data Analysis | Embeddings401k match | Dental insurance | Disability insurance | Hybrid work model | Life insuranceMid-level Full TimeRemote, United States R2d ago
-
Senior-level Full TimeUnited States (Remote) R2d ago