Software Architect - AI

Job highlights

• strong hands-on experience delivering production AI services and web applications end-to-end
• Proven experience building LLM applications (agents / copilots) including RAG,prompt engineering,tool / function calling,and safeguarding (PII handling,prompt injection awareness)
• Build responsive front-end features using JavaScript / TypeScript (Angular preferred

Join Ericsson as a Software Architect AI (Full Stack), leading the design and delivery of production-grade enterprise AI features and full-stack solutions. You will own key technical decisions across UI, backend services, and LLM application architecture spanning agents/copilots, RAG pipelines, evaluation, observability, and security. You will mentor engineers and partner with product and platform teams to ship reliable, scalable AI capabilities in a high-ownership, collaborative environment.

What you will do:

• Architect and deliver end-to-end AI products (UI + services) with ownership for performance, reliability, security, and maintainability; define standards and best practices for the team.
• Build LLM-powered applications (agents/copilots) including tool/function calling, structured outputs, prompt patterns, and guardrails.
• Design and optimize RAG pipelines (ingestion, chunking, embeddings, hybrid retrieval, reranking, citations) and develop REST APIs using Python (FastAPI) and/or Java (Spring Boot) with clean architecture patterns.
• Apply concurrent programming (async IO, multithreading) to optimize AI service throughput; integrate event-driven systems and message buses (Kafka) for scalable workflows.
• Build responsive front-end features using JavaScript/TypeScript (Angular preferred; React/Vue acceptable), including streaming UX (SSE/WebSocket) for chat and assistant experiences.
• Write automated unit/integration tests, contribute to CI/CD pipelines, and containerize and deploy applications using Docker, Kubernetes, and Helm.

The skills you bring:

• B.E/B.Tech/MCA with 10+ years in software engineering; strong hands-on experience delivering production AI services and web applications end-to-end.
• Proven experience building LLM applications (agents/copilots) including RAG, prompt engineering, tool/function calling, and safeguarding (PII handling, prompt injection awareness).
• Deep knowledge of microservices architecture and REST API design using Python (FastAPI); solid OOP and clean architecture principles.
• Front-end proficiency in JavaScript/TypeScript with Angular (React/Vue acceptable); familiarity with Linux/Unix environments and Agile SDLC practices.
• Proficiency with Docker, Kubernetes, Helm, and CI/CD practices; strong understanding of AI evaluation and observability (tracing, metrics, cost monitoring).
• Good to Have: GitLab CI, Apache/Confluent Kafka, cloud-native development (Azure/AWS/GCP), vector databases (Pinecone, FAISS, Elastic), LLM observability tools (LangSmith, Arize), and open-source contributions.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.