Mulțumim pentru trimiterea solicitării! Un membru al echipei noastre vă va contacta în curând.
Mulțumim pentru trimiterea rezervării! Un membru al echipei noastre vă va contacta în curând.
Schița de curs
Introduction to LLMOps
- LLMOps vs MLOps: unique challenges of operating LLMs
- The LLM application lifecycle: prompt, evaluate, deploy, monitor
- Production readiness checklist for GenAI applications
Prompt Management and Versioning
- Prompt templating systems and variable injection
- Semantic versioning for prompts with automated regression testing
- Prompt registries and collaboration workflows
LLM Evaluation at Scale
- Evaluation dimensions: accuracy, relevance, safety, groundedness
- LLM-as-judge metrics and human evaluation pipelines
- Automated eval frameworks: RAGAS, DeepEval, and custom evaluators
- Quality gates in CI/CD for LLM deployments
Safety Guardrails and Content Governance
- Input and output guardrails: NeMo Guardrails and Guardrails AI
- PII detection, toxicity filtering, and topic boundaries
- Jailbreak and prompt injection defense strategies
- Red-teaming LLM applications for safety assurance
LLM Observability and Monitoring
- Telemetry: token usage, latency, cost, and quality metrics
- Drift detection in LLM outputs and embedding spaces
- Session-level tracing for multi-turn agent conversations
- Dashboards and alerting with LangSmith, Arize, and OpenTelemetry
AI Gateway and Model Orchestration
- Multi-provider routing with LiteLLM and Portkey
- Fallback strategies, retry logic, and circuit breakers
- Cost-aware model selection and load balancing
- Rate limiting, quota management, and API key governance
Performance Optimization
- Semantic caching with vector stores and exact-match strategies
- Structured output enforcement with constrained decoding
- Batching, streaming, and concurrency patterns
- Latency optimization across model providers
Governance, Compliance, and Audit
- LLM audit trails: prompt logs, response logs, and decision provenance
- Data residency and privacy considerations for LLM APIs
- Policy-as-code for LLM usage within organizations
- Building an internal LLM operations playbook
Cerințe
- Experience building or integrating LLM-powered applications.
- Familiarity with Python and REST APIs.
- Basic understanding of prompt engineering concepts.
Audience
- ML engineers and MLOps practitioners transitioning to LLM operations.
- Platform engineers responsible for LLM infrastructure.
- Technical leads managing production GenAI deployments.
14 Ore
Mărturii (2)
Stilul interactiv, exercițiile
Tamas Tutuntzisz
Curs - Introduction to Prompt Engineering
Tradus de catre o masina
Un depozit excelent de resurse pentru viitor, stilul instrucționist (plin de umor și cu un nivel de detaliu foarte bun)
Adam - GE Aerospace Poland Sp. z o.o.
Curs - Prompt Engineering for ChatGPT
Tradus de catre o masina
