> Markdown version of [/jobs/ext/2004721-software-engineer-agentic-platforms](https://www.wearedevelopers.com/jobs/ext/2004721-software-engineer-agentic-platforms). 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). --- # Software Engineer, Agentic Platforms - **Company:** XPeng Inc. - **Location:** Santa Clara, United States - **Experience:** Expert - **Salary:** $174,720.0 - $295,680.0 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Databases, Software Debugging, Programming Tools, Distributed Systems, Graph Database, Python (Programming Language), Open Source Technology, Queueing Systems, Software Engineering, Systems Integration, TypeScript, Large Language Models, Multi-Agent Systems, Caching, Data Layers, Kubernetes, Information Technology, Operational Systems, Api Design - **Published:** August 9, 2026 - **Apply:** https://www.dice.com/job-detail/daccd6aa-2809-493e-bc9e-cace7be18191 ## About the Role * Master's degree in Computer Science, Software Engineering, or related fields. * 5+ years building and operating production distributed systems, with demonstrated strength in system design and software engineering fundamentals. * Proficiency in Python and TypeScript; solid grasp of databases, message queues, caching, and API design. * A builder's instinct for automation: a track record of turning manual processes into tools, pipelines, or self-service systems. * Hands-on experience with modern AI coding tooling and LLM APIs, including tool use/function calling. * Experience with agentic systems or task orchestration platforms (workflow engines, multi-agent frameworks, MCP servers, or similar). * Strong cross-team communication skills. Preferred Skill Requirements: * Familiarity with Autonomous Driving terminologies and model development workflows. * Direct customer-facing experience: solutions engineering, technical onboarding, developer relations, or enterprise support. * Experience with data/domain modeling: semantic layers, knowledge graphs, or object models over heterogeneous data sources. * Experience integrating with enterprise or operational systems (internal platforms, legacy APIs, writeback to systems of record). * Experience with evaluation frameworks and observability for LLM applications. * Familiarity with sandboxing/isolation technologies. * Contributions to open-source agent frameworks, MCP servers, or developer tools. * Experience driving adoption of developer tooling within engineering organizations. ## Description * Design, build, and operate production-grade platform services and infrastructure with strong reliability, observability, and performance. * Identify manual, repetitive engineering workflows and eliminate them through self-service automation on the platform. * Build and evolve the agentic layer: agent lifecycle, tool/MCP integrations, sandboxed execution, multi-agent workflows. * Design the semantic data layer that grounds agents: model our systems, workflows, and decision data as connected objects and tools that agents can query and act on. * Build safe action execution paths: connectors to internal and operational systems, staged propose-validate-approve-commit flows, with granular access control and end-to-end decision lineage/audit. * Own system design for new platform capabilities end to end, from requirements through rollout and operations. * Work directly with customers: lead technical onboarding, gather requirements, debug production issues, and turn field feedback into roadmap priorities. * Establish best practices for agent evaluation, observability, and safety guardrails. ## Related Videos - [HTTP headers that make your website go faster](https://www.wearedevelopers.com/videos/1676-http-headers-that-make-your-website-go-faster) - [Kubernetes and Microservices with Multi-Model Databases](https://www.wearedevelopers.com/videos/382-kubernetes-and-microservices-with-multi-model-databases) - [API Design - Getting Started](https://www.wearedevelopers.com/videos/33-api-design-getting-started) - [Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding](https://www.wearedevelopers.com/videos/1604-supercharge-agentic-ai-apps-a-devex-driven-approach-to-cloud-native-scaffolding) - [Event based cache invalidation in GraphQL](https://www.wearedevelopers.com/videos/433-event-based-cache-invalidation-in-graphql) - [Building an agentic software factory: How we rebuilt product development at Pipedrive](https://www.wearedevelopers.com/videos/100261-building-an-agentic-software-factory-how-we-rebuilt-product-development-at-pipedrive) ## Related Articles - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [Everything a Developer Needs to Know About MCP with Neo4j](https://www.wearedevelopers.com/magazine/604-everything-a-developer-needs-to-know-about-mcp-with-neo4j) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [The Best X (Twitter) Accounts for Developers](https://www.wearedevelopers.com/magazine/294-the-best-x-twitter-accounts-for-developers) - [ Dev Digest 213: Petrol Prices, Agentic Workflows, AI Skills and CODE100!](https://www.wearedevelopers.com/magazine/718-dev-digest-213-petrol-prices-agentic-workflows-ai-skills-and-code100) - [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding)