Sapear Inc
AIML Senior Platform Support Engineer/MLOps Engineer-Vector (Contract W2)
Sapear Inc, Charlotte, North Carolina, United States, 28245
Overview
Vector (Contract W2) Location: Charlotte, NC & Irving, Texas (Day 1 onsite) Position: AIML Senior Platform Support Engineer / MLOps Engineer Responsibilities
Vector Databases: Hands-on experience with Elasticsearch or similar; understanding of similarity search, indexing strategies, and embedding management. Linux Systems: Strong command-line skills; shell scripting; system-level monitoring and debugging. Python Programming: Proficient in automation scripting; experience in building AI models, data pipelines, and OpenAI integrations. Big Data Technologies: Familiarity with Hadoop-based platforms like MapR and Hortonworks. AI Platform & Production Support: Experience supporting predictive AI workloads in production; troubleshooting across data ingestion, model inference, and deployment layers; familiarity with CI/CD pipelines and containerization (Docker, Kubernetes); on-call support for GenAI and predictive pipelines (1 week every 6-8 weeks); understanding of enterprise disaster recovery (DR) solutions including backup and restore. Observability & Monitoring: Ability to define and implement observability strategies for AI systems; experience with Splunk, Grafana, ELK stack, OpenTelemetry; proactive monitoring of model failures, latency, and system health. Qualifications
Hands-on experience with Elasticsearch or similar; understanding of similarity search, indexing strategies, and embedding management. Strong Linux command-line and scripting skills; system-level monitoring and debugging. Proficiency in Python for automation, AI models, data pipelines, and OpenAI integrations. Familiarity with Hadoop-based platforms like MapR and Hortonworks. Experience supporting predictive AI workloads in production; troubleshooting across data ingestion, model inference, and deployment layers. CI/CD pipelines and containerization (Docker, Kubernetes). On-call support for GenAI and predictive pipelines. Understanding of enterprise disaster recovery (DR) including backup and restore. Ability to define observability strategies and experience with Splunk, Grafana, ELK, OpenTelemetry. Proactive monitoring of model failures, latency, and system health.
#J-18808-Ljbffr
Vector (Contract W2) Location: Charlotte, NC & Irving, Texas (Day 1 onsite) Position: AIML Senior Platform Support Engineer / MLOps Engineer Responsibilities
Vector Databases: Hands-on experience with Elasticsearch or similar; understanding of similarity search, indexing strategies, and embedding management. Linux Systems: Strong command-line skills; shell scripting; system-level monitoring and debugging. Python Programming: Proficient in automation scripting; experience in building AI models, data pipelines, and OpenAI integrations. Big Data Technologies: Familiarity with Hadoop-based platforms like MapR and Hortonworks. AI Platform & Production Support: Experience supporting predictive AI workloads in production; troubleshooting across data ingestion, model inference, and deployment layers; familiarity with CI/CD pipelines and containerization (Docker, Kubernetes); on-call support for GenAI and predictive pipelines (1 week every 6-8 weeks); understanding of enterprise disaster recovery (DR) solutions including backup and restore. Observability & Monitoring: Ability to define and implement observability strategies for AI systems; experience with Splunk, Grafana, ELK stack, OpenTelemetry; proactive monitoring of model failures, latency, and system health. Qualifications
Hands-on experience with Elasticsearch or similar; understanding of similarity search, indexing strategies, and embedding management. Strong Linux command-line and scripting skills; system-level monitoring and debugging. Proficiency in Python for automation, AI models, data pipelines, and OpenAI integrations. Familiarity with Hadoop-based platforms like MapR and Hortonworks. Experience supporting predictive AI workloads in production; troubleshooting across data ingestion, model inference, and deployment layers. CI/CD pipelines and containerization (Docker, Kubernetes). On-call support for GenAI and predictive pipelines. Understanding of enterprise disaster recovery (DR) including backup and restore. Ability to define observability strategies and experience with Splunk, Grafana, ELK, OpenTelemetry. Proactive monitoring of model failures, latency, and system health.
#J-18808-Ljbffr