Backend / ML-Ops Engineer — Speech Model Deployment & Inference Optimization
Tasks
- Build CI CD pipelines for model promotion
- Configure Kubernetes autoscaling for GPU inference workloads
- Containerize and deploy speech models using Triton Inference Server
- Expose APIs for context biasing rescoring and diagnostics
- Implement low latency on device or edge inference paths
- Implement monitoring dashboards for latency WER drift SNR and packet loss
- Integrate ASR TTS and Speech LLM models into production pipelines
- Integrate failover logic and model switchers for fallback
- Maintain data and model versioning with MLflow or DVC
- Optimize GPU CPU utilization cost and memory footprint
- Optimize inference performance with TensorRT and FP16
Perks/Benefits
- N/A
Skills/Tech-stack
AWS | Azure | Bash | CI/CD | DVC | DevSecOps | Docker | ELK | FP16 | GCP | GPU scheduling | Grafana | Inference Server | Kubernetes | Language Processing | MLflow | Mixed Precision | Model Monitoring | Model Serving | Natural Language | Natural Language Processing | Observability | Prometheus | Python | Quantization | Streaming ASR | TensorRT | Text to Speech | Triton Inference | Triton Inference Server
Related jobs
-
Associate 2 - Engineer (AI Hub - GDC) INR 1800K-2500KCNN | Decision Tree | Deep learning | Huggingface | LSTMMentoring | Work reviewMid-level Full TimeHyderabad, Telangana, India5h ago
-
Executive-level Full TimeHyderabad, Telangana, India5h ago
-
Senior-level Full TimeIndia - Bengaluru; India - Hyderabad7h ago
-
GCP Data Engineer INR 2000K-3000KApache Airflow | Apache Spark | BigQuery | Cloud Composer | Cloud DataflowSenior-level Full TimeIndia - Bengaluru; India - Hyderabad7h ago
-
AWS | Agentic AI | Apache Spark | Databricks | Generative AICollaborative global engineering culture | Continuous learning | Flexible work environment | Opportunity to work on cutting edge GenAI | Remote-friendly work environmentSenior-level Full TimeIndia8h ago
-
Senior Data Engineer INR 3000K-4200KAWS | Access Management | Amazon Neptune | Apache Airflow | Apache KafkaCareer advancement | Hybrid work options | Professional development programs | Remote work options | Training programsSenior-level Full TimeBengaluru8h ago
-
Data Engineer INR 1500K-2000KAWS Glue | Access Control | Amazon EMR | Amazon Snowflake | Apache AirflowMid-level Full TimeIndia8h ago
-
API | Agile | Apache Airflow | Bitbucket | CI/CDEmployee assistance program | Flexible working environment | LinkedIn Learning | Volunteer time offMid-level Full TimeChennai, India8h ago
-
Senior-level Full TimeIndia9h ago
-
Lead Software Engineer INR 3000K-4500KAWS | CI/CD | DevOps | Docker | EMRCareer development opportunities | Comprehensive benefits | Continuous learning | Flexible working hours | Work-life balanceSenior-level Full TimeMumbai, India10h ago
-
Staff Software Engineer - Data INR 3200K-4600KAWS Lambda | Airflow | Ansible | Apache Flink | Apache SparkSenior-level Full TimeBengaluru, INDIA, India10h ago
-
.NET | APIs | AWS | Alerting | AzureAdoption leave | Employee assistance program | Health care benefits | Maternity leave | Mental wellness programsSenior-level Full TimeIndia10h ago
-
Engineering Expert - AI & Data Products, Runtime Platform INR 3000K-4000KAI Agents | Apache Spark | Argo CD | CI/CD | Data ContractsSenior-level Full TimeBangalore, KA, IN, 56006612h ago
-
AI Data Engineer INR 2000K-3300KAWS | Agent memory | Audio Processing | Batch Processing | Cloud ComputingEquityMid-level Full TimeNew Delhi12h ago
-
Data Engineer, Analytics Engineering, VP INR 1500K-6000KAWS Data | AWS Data Catalog | AWS Glue | AWS Glue Catalog | AWS Glue Data GovernanceExecutive-level Full TimeBengaluru, India14h ago
-
AI Engineer - Full Stack INR 1200K-2500KAI output validation | AI tools | Agile | C++ | Code reviewEthical AI Guidelines | Learning opportunities | Onsite interview optionMid-level Full TimeIND-Pune-Smartworks, India14h ago
-
Data Engineer With Data Observability INR 1500K-2000KAWS | Agile | Airflow | CI/CD | Cloud OperationsMid-level Full TimeBangalore, IN14h ago
-
Principal Data Engineer INR 3000K-4000KAWS | Agile | Amazon EC2 | Amazon S3 | Automated testingBereavement leave | Diversity, equity, & inclusion programs | Employee assistance program | Employee referral program | Healthcare insuranceSenior-level Full TimeIND - Bengaluru, India14h ago
-
AI Research Engineer - Applied AI INR 2000K-3000KAPI Design | AWS SageMaker | Anomaly Detection | Azure Machine Learning | Bias auditingAsynchronous culture | Distributed team | Remote workMid-level Full TimeRemote - REMOTE, India, India R14h ago
-
Senior Data Engineer INR 2000K-2250KApache Airflow | CI/CD | Cloud Composer | Cloud Dataflow | Cloud StorageSenior-level Full Time111443-IND-HYDERABAD-INTL HYD WF CENTRE BLK B8 …14h ago
-
Principal Engineer - Java with Gen AI INR 2000K-3465KAgent Frameworks | Azure | Cloud Native | Concurrency | EmbeddingsSenior-level Full Time110380-IND-BENGALURU-INTL BLR Twr-1&2 CARNATION, India14h ago
-
Mid-level Full Time110380-IND-BENGALURU-INTL BLR Twr-1&2 CARNATION, India14h ago
-
AI Engineer INR 700K-900KAPI Development | Agentic environments | Agile | Apache Kafka | Cloud NativeMid-level Full Time110380-IND-BENGALURU-INTL BLR Twr-1&2 CARNATION, India14h ago
-
Mid-level Full Time110380-IND-BENGALURU-INTL BLR Twr-1&2 CARNATION, India14h ago
-
Senior Software Engineer- Gen AI INR 2000K-3465KAgile Scrum | Artificial Intelligence | Embeddings | GenAI | GitSenior-level Full Time111443-IND-HYDERABAD-INTL HYD WF CENTRE BLK B8 …14h ago