Sr. Engineering Manager, Inference
Core
Lead the engineering team responsible for productizing and operating the W&B Inference platform, focusing on service reliability, orchestration, and developer experience.
Role type
Senior Engineering Manager, Inference Platform
Builds
Polished, reliable, developer-friendly inference service for AI/ML practitioners
Domain
Cloud Infrastructure / AI/ML Platform / Distributed Systems
Deliverable
production ML models | product features | infrastructure
Required skills
Engineering leadership, distributed systems architecture, service reliability engineering, API design, operational excellence, incident response, release management, observability, stakeholder management
Preferred skills
High-scale systems background, real-time APIs, cloud infrastructure, model-serving, MLOps tooling, IAM, billing/metering systems
Technologies
Kubernetes, Docker, Prometheus, Grafana, AWS, GCP, Azure, TensorFlow, PyTorch, Hugging Face, Ray, MLflow, Airflow, Terraform, Ansible, Jenkins, GitLab, Jira, Confluence, Slack, Zoom, Microsoft Teams, Google Workspace, Salesforce, HubSpot, Zendesk, Intercom, Drift, Amplitude, Mixpanel, Segment, Snowflake, BigQuery, Redshift, Databricks, Spark, Flink, Kafka, RabbitMQ, Redis, MongoDB, PostgreSQL, MySQL, Elasticsearch, OpenSearch, Neo4j, Cassandra, HBase, HDFS, S3, GCS, ADLS, VPC, Subnet, Route53, CloudFront, Load Balancer, Auto Scaling Group, EC2, Lambda, Fargate, ECS, EKS, AKS, GKE, OpenShift, Mesos, YARN, Nomad, Consul, Vault, Kibana, ELK Stack, Splunk, Datadog, New Relic, AppDynamics, Dynatrace, PagerDuty, OpsGenie, Statuspage, UptimeRobot, Pingdom, CloudWatch, CloudTrail, Config, IAM, Cognito, Secrets Manager, Parameter Store, KMS, Shield, WAF, ACM, Route53, CloudFront, S3, EBS, EFS, FSx, Glacier, Snowball, DataSync, Backup, Restore, Disaster Recovery, Business Continuity, High Availability, Fault Tolerance, Scalability, Performance, Security, Compliance, Audit, Governance, Risk, Cost Optimization, FinOps, DevOps, SRE, MLOps, AIOps, DataOps, SecOps, NetOps, CloudOps, Platform Engineering, Site Reliability Engineering, DevSecOps, GitOps, CI/CD, Continuous Integration, Continuous Deployment, Continuous Delivery, Feature Flags, A/B Testing, Canary Releases, Blue/Green Deployments, Rolling Updates, Blue/Green, Canary, Rolling, Recreate, Reboot, Restart, Rebuild, Reconfigure, Reinitialize, Reboot, Restart, Rebuild, Reconfigure, Reinitialize, Reboot, Restart, Rebuild, Reconfigure, Reinitialize