Key Responsibilities :

- Design and implement CI/CD pipelines for models, prompts, agents, and supporting infrastructure across development, test, and production environments.

- Build and maintain deployment automation for AI workloads, including versioning and rollback mechanisms, environment promotion workflows, and runtime safeguards.

- Set up and operate observability for AI applications and agents : tracing, monitoring, alerting, token-consumption analysis, latency tracking, and incident diagnostics.

- Implement evaluation pipelines and acceptance gates for quality, groundedness, task adherence, safety, and agent-specific behaviour.

- Drive prompt lifecycle management, RAG optimisation, and semantic retrieval tuning, and integrate vector- or search-based knowledge components where needed.

- Partner with security, engineering, and data teams to build identity, secrets management, compliance controls, and cost optimisation into the operating model.

- Contribute to platform automation, runbooks, and on-call readiness, and lead post-incident reviews that improve production AI services.

Qualifications :

- DevOps and platform engineering : Experience operating production cloud workloads with CI/CD, monitoring, and infrastructure automation.

- MLOps / LLMOps / AgentOps : Hands-on practice in deployment, monitoring, retraining or re-evaluation, and controlled release management for AI systems.

- Observability : Strong grasp of logs, metrics, traces, runtime telemetry, and production diagnostics for AI workloads.

- Generative AI engineering : Familiarity with retrieval-augmented systems, prompt engineering, tool-calling flows, and agent behaviour debugging.

- Operational excellence : A reliability-first mindset with strong attention to security, incident response, and cost-performance trade-offs.