Note: The job is a remote job and is open to candidates in USA. Tredence Inc. is seeking a Senior GenAI & Agentic AI Platform Engineer to architect, build, and operate an enterprise-grade AI platform. This role involves leading the design and implementation of autonomous agentic systems while ensuring high standards for performance, security, and observability.
Responsibilities
- Architect and build a resilient, multi-agent AI platform capable of scaling seamlessly to 100s of production agents
- Design robust agent runtime capabilities, including state persistence, memory management (short/long-term), and context window optimization
- Optimize non-functional requirements across the platform, including token usage, end-to-end latency SLAs, throughput, and compute efficiency
- Implement enterprise AI observability standards—including tracing, evaluation, and monitoring—using tools such as OpenTelemetry, Arize, and MLflow
- Integrate end-to-end security and governance protocols (e.g., SAST/DAST, RBAC, line-of-sight auditing) into agent workflows and platform deployment pipelines
- Build reusable SDKs, implementation templates, and standard frameworks for rapid agent onboarding and platform adoption
- Enhance CI/CD automation, heartbeat monitoring, and automated validation for agent deployments
- Collaborate with enterprise architects and product teams to translate platform goals into clear, actionable sprint execution plans
Skills
- 8–10 years of AI/Ml experience with significant focus on building GenAI and agentic solutions
- Strong hands-on expertise in Azure and Databricks (Unity Catalog, Model Serving, MLflow)
Company Overview
Company H1B Sponsorship