Inference Optimization Architect, Speech AI
Tasks
- Apply knowledge distillation
- Apply model pruning
- Apply model quantization
- Build automated model optimization pipelines
- Collaborate with model researchers to deploy to production
- Design speech model serving infrastructure
- Develop CUDA custom kernels
- Implement encoder caching
- Improve batching strategies
- Leverage CUDA and TensorRT acceleration
- Monitor inference costs and resource utilization
- Optimize inference across GPUs and platforms
- Optimize multi threaded inference pipelines
- Optimize streaming latency and throughput
- Profile and benchmark inference bottlenecks
- Use Nsight Compute for GPU debugging
- Use Nsight Systems for GPU profiling
Perks/Benefits
- N/A
Skills/Tech-stack
Batching | CNN | CUDA | Computer Architecture | Dynamic Shapes | GPU Profiling | Inference Server | JAX | Kernel development | Knowledge Distillation | Latency Tuning | Memory Management | Model Compression | Nsight Compute | Nsight Systems | Operating Systems | Process scheduling | Pruning | PyTorch | Python | Quantization | RNN | TRT-LLM | TensorRT | Thread synchronization | Torchserve | Transformers | Triton Inference | Triton Inference Server | VLLM
Education
Related jobs
-
Mid-level Full TimeGurugram, Haryana, India8h ago
-
Sr. Software Engineer (AI/ML) (PhD / Postdoc) INR 1500K-2400KCausal Inference | Deep learning | Generative AI | Language Processing | Machine LearningAccess to large clinical dataset | Collaboration with healthcare partners | Conference publication support | Research freedomSenior-level Full TimeHyderabad, India9h ago
-
Mid-level Full TimeGurugram, Haryana, India9h ago
-
AI | AWS | Agile | Ansible | AutosysSenior-level Full TimeBengaluru, Karnataka, India9h ago
-
IT Data Engineer II INT INR 1800K-2500KApache Spark | Cloud Cost Optimization | Cloud platform | Cost Optimization | Data GovernanceMid-level Full TimeBangalore, India15h ago
-
Data Engineer - VOIS INR 2000K-2040KApache Airflow | Apache Spark | BigQuery | CI/CD | Cloud ComposerCollaborative environment | Flexible inclusive workplace | Learning opportunitiesMid-level Full TimePune, IN15h ago
-
AWS CloudFormation | Amazon Kinesis | Amazon Redshift | Amazon S3 | Amazon Web ServicesEqual opportunity employer | Fast track growth opportunities | Great place to workSenior-level Full TimeHyderabad, Office Level 3 & 4, …15h ago
-
TTT-SAP-Python Gen AI-Tax Senior INR 2000K-4512KAI Core | AI Launchpad | API Management | CI/CD | Cloud ALMSenior-level Full TimeBengaluru, KA, IN, 56001615h ago
-
Entry-level Full TimeBangalore, India15h ago
-
Senior-level Full TimeIndia - Chennai15h ago
-
Data Architect INR 2520K-3380KAmazon Redshift | Bash | Business Requirements | Case documentation | Customer DataSenior-level Full TimeBangalore, India R15h ago
-
Data engineer (Azure Databricks) INR 1500K-2500KAmazon Web Services | Apache Airflow | Apache Kafka | Apache Spark | AzureMid-level Full TimeChennai, Tamil Nadu, India15h ago
-
Data Engineer INR 3000K-4000KAgile | Azure | Azure IAM | Azure Networking | Azure StorageBe Well programs | Certification support | Coaching | Continuous feedback | Hybrid workMid-level Full TimeINMANBP Bangalore (INMANBP) Manyatha, India15h ago
-
Data Engineering Lead - MSC INR 2520K-3380KAbinitio | Airflow | Azure Data | Azure Data Factory | Azure Data LakeRelocation supportSenior-level Full TimeBusiness Office (Joy House 2) - …15h ago
-
Associate Data Engineer INR 1500K-2000KAWS | CCPA | Data Architecture | Data Governance | Data ModelingMid-level Full TimeIndia - Hyderabad15h ago
-
Senior AI/ML Engineer INR 2500K-5000KAI Document Intelligence | AI Services | API Design | Agent Orchestration | Agent systemsSenior-level Full TimeBangalore - RGA Tech Park, India15h ago
-
Software Engineering LMTS- ML Engineer INR 2500K-4500KEmbeddings | Fine Tuning | LLM | Machine Learning | Machine Learning PipelinesSenior-level Full TimeIndia - Bangalore15h ago
-
Associate Database Reliability Engineer INR 1200K-2500KBash | CentOS | Cloud infrastructure | DNS | DRSMid-level Full TimePune, India15h ago
-
Software Development Engineer 1 INR 2200K-4200KAI Agents | AWS | Azure | CI/CD | DockerContinuous learning | Flexible experimentation | Innovation culture | Mentorship | Open collaborationNone Full TimeAPAC - India - Bengaluru - …15h ago
-
Software Development Engineer 4 INR 2500K-4500KAWS EMR | Airflow | Apache Spark | Data Ingestion | Data LakeSenior-level Full TimeNoida, India R15h ago
-
Entry-level Full TimeBangalore, India15h ago
-
IT Data Engineer II INT INR 1800K-2500KApache Spark | Cloud platform | Dashboards | Data Governance | Data ModelingMid-level Full TimeBangalore, India15h ago
-
Sr. Big Data Engineer INR 2400K-3500KAWS | Apache Spark | Azure | Cloud Platforms | Data ArchitectureTravel opportunitiesSenior-level Full TimeRemote - India R22h ago
-
Senior-level Full TimeBengaluru, Karnataka, India1d ago
-
AWS Data Architect INR 1500K-3000KAWS Glue | Amazon Athena | Amazon EMR | Amazon Kinesis | Amazon RedshiftSenior-level Full TimeKochi, Kerala, India1d ago