USA_Engineer

Pay Rate Range: $ 53.57- 55.14/hr. GBAMS ID: 10522311 AI Engineer Job Description: "• 5+ years building LLM/agentic apps; strong Python. • Hands on with Google Gemini (prompting, tool use/function calling, structured outputs) and ADK (planning/orchestration/memory). • GCP fluency: IAM, Cloud Run/GKE, Vertex AI, Cloud Storage, Cloud Logging/Monitoring, Secret Manager, Cloud Build/Cloud Deploy. • CI/CD: Terraform, Jenkins and AWS Code Pipeline • Storage: Alloy DB, Spanner DB, Neo4j, etc. • Observability expertise: Open Telemetry (traces/metrics/logs), Dynatrace, Splunk • Data & evaluation: dataset curation, prompt/version management, offline evals (accuracy, hallucination, safety), online metrics (latency, cost, win rate)" Role Descriptions: Responsibilities Design build agentic systems using Gemini ADK (tool use| planning| memory| orchestrations) and deploy them on GCP (Cloud RunGKE| Vertex AI endpoints).Observability of AI agents monitor the runtime performance of the Agents and related metrics Productionize agent workflows for SRE use cases incident triage| log trace summarization| anomaly detection| remediation suggestions| runbook generation| and post incident reviews. Integrate with developer ecosystem GitHubCI CD| policy checks| secrets management| feature flags| and progressive delivery (canaryblue green) for agent versions and prompts. Evaluate improve run offline online evaluations| drive mode lagent quality close the loop with feedback from SREs. Required qualifications1 years building LLMagentic apps strong Python. Hands on with Google Gemini (prompting| tool use function calling| structured outputs) and ADK (planning orchestration memory).GCP fluency IAM| Cloud RunGKE| Vertex AI| Cloud Storage| Cloud Logging Monitoring| Secret Manager| Cloud Build Cloud Deploy. CICD Terraform| Jenkins and AWS Code Pipeline Storage AlloyDB| Spanner DB| Neo4j| etc. Observability expertise Open Telemetry (traces metrics logs)| Dynatrace| Splunk Data evaluation dataset curation| prompt version management| offline evals (accuracy| hallucination| safety)| online metrics (latency| cost| win rate)How we measure success MTTAMTTR for critical incidents attributable to agent assistance SLO compliance for agent endpoints and orchestrations Observability coverage of agent tool calls with correlated trace spans structured logs Quality offline online evals (win rate| factuality| safety) meeting defined gates Skills: Digital : Artificial Intelligence(AI) Experience Required: 2-4 Skills: Category Name Required Importance Experience SkillCategoryTest1_MN Digital : Python Yes 1 4-7 years

Created: 2026-03-10