Hello eager tech expert!

For this Azure-based AI platform, we are seeking a skilled AI Engineer with strong Python backend expertise to design, build, and operate production-grade LLM and retrieval systems across chat, ingestion, and indexing services.

In this role, you will own end-to-end AI application flows: multi-agent orchestration, vector search quality, external/internal data ingestion pipelines, and robust API delivery. You will work across FastAPI and Azure Functions services, integrating Azure OpenAI, Azure AI Search, Cosmos DB, SQL databases, and Snowflake-backed analytics to deliver reliable and secure enterprise intelligence features.

You will collaborate closely with product, data, and platform stakeholders to improve answer quality, reduce operational risk, and scale AI capabilities under strict governance, privacy, and observability requirements.

Additionally, you will support architecture and operations topics such as incident troubleshooting, model behavior diagnostics, prompt/workflow tuning, and technical documentation for onboarding and handover.

You’ll break new ground by

Key Responsibilities:

AI Engineering & LLM Systems

• 3+ years of experience in AI-enabled backend engineering, including at least 2+ years working with production LLM applications.

• Hands-on experience with Azure OpenAI (chat, embeddings, model fallback patterns, structured outputs, and rate-limit/error handling).

• Experience implementing multi-step or agentic workflows (for example planning, retrieval, synthesis, validation, fallback/recovery paths).

• Strong understanding of RAG design, retrieval quality tuning, chunking strategies, citation grounding, and relevance validation.

• Experience with LangChain/LangGraph or equivalent orchestration frameworks.





Platform Engineering, Security & Delivery

• 5+ years of Python backend engineering in production environments.

• Strong FastAPI and Azure Functions expertise ( async patterns, deployment, and operations).

• Proven ability to build resilient AI backend services with robust validation, RBAC, clean error handling, and modular/testable architecture.

• Solid security and privacy practice: identity-based access, secret management, least-privilege design, and PII-safe processing aligned with enterprise governance.

• Robust reliability mindset: unit/integration testing, observability, incident response, root-cause analysis, and performance/cost tuning.

• Effective cross-functional collaboration, clear technical documentation, and CI/CD ownership for stable releases.

Create a better #TomorrowWithUs!

We value your unique identity and perspective and are fully committed to providing equitable opportunities and building a workplace that reflects the diversity of society. Come bring your authentic self and create a better tomorrow with us.

This role is based in Bangalore. But you’ll also get to visit other locations in India and globe, so you’ll need to go where this journey takes you. In return, you’ll get the chance to work with teams impacting entire cities, countries and the shape of things to come. We’re Siemens. A collection of over 379,000 minds building the future, one day at a time in over 200 countries. We're dedicated to equality, and we welcome applications that reflect the diversity of the communities we work in. All employment decisions at Siemens are based on qualifications, merit and business need. Bring your curiosity and creativity and help us craft tomorrow.

Find out more about Siemens careers at:

📌 Sr. AI Engineer (Bengaluru)
🏢 Leading
📍 Bengaluru