> Markdown version of [/jobs/ext/4519503-technical-architect](https://www.wearedevelopers.com/jobs/ext/4519503-technical-architect). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Technical Architect

- **Company:** Yantran Llc
- **Location:** San Jose, CA, United States
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Cloud Engineering, Continuous Integration, Data Centers, Distributed Systems, Key Management, Search Technologies, Workflow Management Systems, Computer Network Operations, LangChain, Retrieval-Augmented Generation, Large Language Models, Prompt Engineering, Model Validation, Llamaindex, Agentic-AI, Event Driven Architecture, Kubernetes, CrewAI, AutoGen, Invoking Functions, Api Gateway, Automation Anywhere, Microservices
- **Published:** November 2, 2026
- **Apply:** https://www.juju.com/job/16_dd5fc68a

## About the Role

Strong architecture experience with GenAI, LLM applications, RAG, vector search, agentic AI, and multi agent orchestration.
Experience with frameworks such as LangGraph, LangChain, CrewAI, AutoGen, LlamaIndex, or equivalent.
Strong understanding of enterprise system design, including distributed architecture, event driven design, API first design, HA/DR, observability, and security.
Experience with tool/function calling, workflow orchestration, agent state management, prompt management, and model governance.
Knowledge of network operations concepts such as incidents, alarms, telemetry, topology, RCA, configuration drift, change management, and remediation.
Experience with cloud native architecture, Kubernetes, microservices, CI/CD, secrets management, and API gateways.
Strong stakeholder communication skills for leadership, engineering, operations, security, and business teams.
Preferred Skills
Experience with telecom, service provider, data center, or large enterprise infrastructure environments.
Experience defining responsible AI frameworks, model risk controls, agent evaluation standards, and audit safe AI workflows.