Описание вакансии
Обязанности
•Build and operate LLM gateway
•Create caching and guardrails for latency and safety
•Develop evals and experimentation infrastructure
•Handle PII detection and policy enforcement
•Implement cost control and budgets quotas attribution
•Instrument LLM observability traces spans prompt response capture
•Maintain reliability with SLOs on call incident response postmortems
•Manage model provider keys routing rate limits failover quotas
Условия
•Car lease policy
•Dental insurance
•Fitness benefit
•Gratuity
•Group medical insurance
•Mental health support
•Personal accident insurance
•Preventive healthcare
•Term life insurance
•Vision insurance
Технологии: AWS, Alerting, Caching, ClickHouse, Datadog, FinOps, GCP, GitLab CI, GitOps, Guardrails, Incident Response, Kubernetes, Litellm, Logging, Loki, Metrics, Observability, On-Call, PII Detection, Prometheus, Prompt Tracing, Python, RAG, SLOs, Terraform, Tokens