ML Performance Engineer
Tasks
- Build benchmark suites and regression frameworks
- Collaborate with ML and platform teams to embed performance best practices
- Document performance tuning playbooks and share findings
- Drive compiler level optimizations with Triton XLA TorchInductor TVM
- Evaluate new hardware and software offerings
- Identify and eliminate bottlenecks in data loading model compute communication memory
- Improve cost efficiency with model architecture hardware selection scheduling
- Optimize AI training and inference pipelines for throughput latency cost
- Optimize KV cache continuous batching speculative decoding for LLM serving
- Optimize data pipelines sharding strategies storage access patterns
- Optimize distributed training with tensor parallelism pipeline parallelism FSDP ZeRO style sharding
- Translate AI systems research into production improvements
- Tune attention implementations with FlashAttention paged attention
- Tune quantization sparsity pruning strategies
Perks/Benefits
Skills/Tech-stack
Attention Optimization | Benchmarking | C++ | Compiler optimization | Continuous batching | DeepSpeed | Distributed Training | Distributed inference | FSDP | FlashAttention | GPU Architecture | KV cache | LLM Inference | Memory Management | Model Parallelism | Paged Attention | Pipeline parallelism | Profiling | Pruning | Python | Quantization | Regression testing | Sparsity | Speculative decoding | TVM | Tensor Parallelism | TorchInductor | Triton | XLA | Zero
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 R8d ago
-
AI Forward Deployed Engineer | $120K-$150K + Hybrid + Equity | AI-Based Outage Intelligence Company A USD 120K-150KAI workflows | API Development | Automation | Backend Development | PythonDirect impact on company growth | Equity | Fast moving startup environment with significant ownership | Hybrid work environment | Opportunity to define internal systems and customer experienceMid-level Full TimeKing of Prussia, PA, United States R14h ago
-
Generative AI Engineer USD 100K-150KAdapter-Tuning | Benchmarking | DPO | Direct Preference Optimization | Distributed TrainingSenior-level Full TimeUnited States - Remote R21h ago
-
Edge Computing AI Engineer USD 100K-150KC++ | Core ML | Edge inference | Energy Efficiency | Federated LearningCareer growth | Remote workSenior-level Full TimeUnited States - Remote R21h ago
-
AI Scientist USD 100K-150KAblation Studies | Accelerator hardware | Agentic Systems | Computer Vision | Data QualityRemote workSenior-level Full TimeUnited States - Remote R21h ago
-
Senior-level Full TimeUnited States - Remote R21h ago
-
Senior-level Full TimeUnited States - Remote R21h ago
-
Machine Learning Data Engineer USD 100K-150KApache Beam | CI/CD | Data Drift | Data Lineage | Data ModelingRemote workSenior-level Full TimeUnited States - Remote R21h ago
-
Senior-level Full TimeUnited States - Remote R21h ago
-
Large Language Model Specialist USD 100K-150KAdapter methods | Attention Optimization | DPO | Evaluation methodology | FSDPSenior-level Full Time85295, AZ R21h ago
-
LLM Prompt Specialist USD 100K-150KAgentic Workflows | Embeddings | Evaluation Frameworks | Fine Tuning | GuardrailsMid-level Full TimeUnited States - Remote R21h ago
-
LLM Engineer USD 100K-150KAdapter methods | Benchmarking | DPO | Distributed Training | Efficient AttentionSenior-level Full TimeUnited States - Remote R21h ago
-
LLM Engineer USD 100K-150KAdapters | DPO | Dataset curation | Deep reinforcement learning | Efficient AttentionSenior-level Full TimeUnited States - Remote R21h ago
-
Machine Learning Infrastructure Engineer USD 100K-150KAPI Gateway | Abuse detection | Automated rollback | Autoscaling | C++Senior-level Full TimeUnited States - Remote R21h ago
-
Machine Learning Research Engineer USD 100K-150KAccelerators | Computer Vision | Data Quality | Data quality monitoring | Dataset labelingCareer growth potential | Remote workSenior-level Full TimeUnited States - Remote R21h ago
-
Senior DS/ML Scientist II- Search Science USD 115K-195KDeep learning | Feature Engineering | Generative AI | Information Retrieval | Language ProcessingSenior-level Full TimeUS Remote, United States R21h ago
-
MLOps Engineer USD 100K-150KAPI Gateway | Abuse detection | Automated rollback | Autoscaling | C++Career growth | Remote workSenior-level Full TimeUnited States - Remote R21h ago
-
Prompt Engineer USD 100K-150KAgentic Workflows | Chunking | Embeddings | Evaluation Frameworks | Fine TuningCareer growth | Remote workSenior-level Full TimeUnited States - Remote R21h ago
-
Robotics Engineer USD 100K-150KBehavior Trees | C++ | Computer Vision | Concurrent Systems | Control SystemsSenior-level Full TimeUnited States - Remote R21h ago
-
Robotics Solutions Engineer USD 100K-150KBehavior Trees | C plus plus | Concurrent programming | Control Systems | Data collectionCareer growth opportunities | Health and benefits | Remote workMid-level Full TimeUnited States - Remote R21h ago
-
ML Security Engineer USD 100K-150KAccess Control | Access Management | Adversarial ML | Authorization | Cloud SecuritySenior-level Full TimeUnited States - Remote R21h ago
-
Hadoop Solutions Developer USD 100K-150KAWS EMR | Airflow | Apache Atlas | Apache Flink | Apache HudiRemote workSenior-level Full TimeUnited States - Remote R21h ago
-
AI Optimization Engineer USD 100K-150KBenchmarking | C++ | Cache optimization | Compiler optimization | Continuous batchingCareer growthSenior-level Full TimeUnited States - Remote R21h ago
-
Artificial Intelligence (AI) Engineer USD 78K-145K.NET | Agentic Workflows | CI/CD | Csharp | Data PipelinesRemote workEntry-level Full TimeDallas, Texas, United States R22h ago
-
Data Analytics - Associate USD 110K-150KA/B | A/B Testing | B testing | DBT | Data EngineeringEmployer-Matched Retirement Plan | Flexible remote work Friday | Parental leave | Subsidized healthcare | TelemedicineSenior-level Full TimeNew York, New York, United States R23h ago