Principal Engineer - Generative AI Infra Capabilities
INR 2500K-4500K (estimate) Senior-level Full Time
Tasks
- Advise leadership on enterprise technology solutions
- Automate CI CD for infra and model artifacts with canary and rollback
- Benchmark disaggregated inferencing prefill and decode
- Collaborate across product and technical teams to align delivery milestones
- Configure GPU estate hygiene and change controls
- Design GPU cluster topologies for high throughput inferencing
- Harden environments with disaster recovery failover runbooks
- Implement observability tracing and evaluation workflows
- Implement vLLM and TensorRT LLM based inferencing pipelines
- Integrate Triton Inference Server for multi-model serving
- Lead strategy for long term large scale technical challenges
- Manage API gateway endpoints for model deployments
- Mentor engineers and present architecture readouts
- Operationalize OpenShift AI for GPU scheduling and preemption
- Optimize KV cache strategies for LLM and SLM runtimes
- Publish infrastructure runbooks for development through production
- Tune CUDA kernels and NCCL collectives for performance
Perks/Benefits
- N/A
Skills/Tech-stack
Apigee | Arize | CI/CD | CUDA | CUDNN | Disaster Recovery | Docker | GKE | GPU infrastructure | Generative AI | H100 | H200 | Helm | Inference Server | JFrog | Kubernetes | Kustomize | MIG | MLOps | NCCL | NVLink | NVSwitch | Network Storage | Network Storage Topology | Observability | OpenAPI | OpenAPI Specification | OpenShift | OpenShift AI | Overwatch | RHOAI | SLA | SLO | Storage topology | TensorRT-LLM | Triton Inference | Triton Inference Server | VLLM
Education
N/A
Related jobs
-
Convolutional Neural Networks | Deep learning | Generative AI | Google Gemini | LLM PromptsFlexibility programs | Inclusive benefits | Mentorship | Wellbeing supportMid-level Full TimeKolkata DN 57, India2h ago
-
API | Amazon Web Services | Apache Airflow | Apache Hadoop | Azure DataFlexibility programs | Inclusive benefits | MentorshipMid-level Full TimeKolkata DN 57, India2h ago
-
Apache Airflow | Apache Hadoop | Apache Spark | App Service | Azure AppFlexibility programmes | Inclusive benefits | MentorshipSenior-level Full TimeKolkata DN 57, India2h ago
-
Apache Airflow | Apache Spark | Azure Cosmos | Azure Cosmos DB | Azure DataSenior-level Full TimeKolkata DN 57, India2h ago
-
Apache Airflow | Apache Hadoop | Apache Kafka | Apache Spark | App ServiceSenior-level Full TimeKolkata DN 57, India2h ago
-
IN_Manager_Data Analyst_Data and Analytics_Advisory_Bangalore INR 1500K-2000KApache Airflow | Apache Flink | Azure | Azure DevOps | CI/CDMid-level Full TimeBengaluru Millenia, India2h ago
-
API Integration | Agile | Apache Airflow | Apache Hadoop | Apache KafkaFlexibility programs | Inclusive benefits | Mentorship | Wellbeing supportSenior-level Full TimeKolkata DN 57, India2h ago
-
Amazon Web Services | Apache Airflow | Apache Databricks | Apache Hadoop | Apache SparkSenior-level Full TimeKolkata DN 57, India2h ago
-
API ingestion | Agile | Apache Airflow | Apache Hadoop | Apache KafkaFlexibility programmes | Inclusive benefits | Mentorship | Wellbeing supportSenior-level Full TimeKolkata DN 57, India2h ago
-
Azure DevOps | Azure Machine Learning | Data Pipelines | MLOps | Machine LearningFlexibility programmes | Inclusive benefits | Mentorship | Wellbeing supportMid-level Full TimePune, India2h ago
-
API | API Development | Agentic AI | Artificial Intelligence | BaggingFlexible working arrangements | Inclusive benefits | Mentorship | Wellbeing supportMid-level Full TimeKolkata DN 57, India2h ago
-
API | Agentic AI | Apache Airflow | Apache Hadoop | Azure DataMid-level Full TimeKolkata DN 57, India2h ago
-
IN_Manager_Data Analyst_Data and Analytics_Advisory_Bangalore INR 1500K-2000KApache Airflow | Apache Flink | Azure DevOps | CI/CD | Cloud DataFlexible work arrangements | Mentorship | Wellbeing supportMid-level Full TimeBengaluru Millenia, India2h ago
-
Apache Airflow | Apache Hadoop | Apache Spark | App Service | Azure AppFlexibility programmes | Inclusive benefits | MentorshipSenior-level Full TimeKolkata DN 57, India2h ago
-
API ingestion | Apache Airflow | Apache Kafka | Apache Spark | App ServiceFlexible work programs | Inclusive benefits | Mentorship | Work-life balanceSenior-level Full TimeKolkata DN 57, India2h ago
-
API ingestion | Agile | Apache Airflow | Apache Hadoop | Apache SparkFlexibility programs | Inclusive benefits | MentorshipSenior-level Full TimeKolkata DN 57, India2h ago
-
Apache Airflow | Apache Hadoop | Apache Spark | App Service | Azure AppFlexibility programmes | Inclusive benefits | Mentorship | Wellbeing supportSenior-level Full TimeKolkata DN 57, India2h ago
-
Agile | Apache Spark | App Service | Azure App | Azure App ServiceFlexibility programmes | Inclusive benefits | Mentorship | Wellbeing supportSenior-level Full TimeKolkata DN 57, India2h ago
-
Apache Airflow | Apache Hadoop | Apache Spark | App Service | Azure AppSenior-level Full TimeKolkata DN 57, India2h ago
-
Senior-level Full TimeMaharashtra, Mumbai, India12h ago
-
AWS | AWS Glue | AWS Lambda | Amazon Athena | Amazon EMRAI certifications | Ethical AI focus | Mentorship | World-class trainingSenior-level Full TimeIndia-Hyderabad13h ago
-
Senior-level Full TimeMaharashtra, Mumbai, India13h ago
-
Senior-level Full TimeIN-TN-Chennai13h ago
-
Senior-level Full TimeIN-TN-Chennai13h ago
-
Senior-level Full TimeIN-TN-Chennai13h ago