Senior AI / Automation SME [T500-29460]

Talent500 is hiring for one of its clients.

Who are we:

Core Insurance Platforms (CIP) is Zurich’s global capability responsible for building, running, and evolving core insurance technology. We set a unified, scalable operating model—covering governance, standards, architecture, service delivery, and reuse—so our business units can deliver at speed and scale.

CIP is the strategic steward of Zurich’s Guidewire ecosystem, aligning platform roadmaps to business strategy while driving stability, modernization, reduced supplier dependency, and long term cost efficiency.

India delivery center is one of our global delivery and capability hub. We bring together experts in AI, engineering, analysis, quality, and architecture to deliver product & process solutions, application run services, change and transformation initiatives, and centralized platform services across both on prem and Guidewire Cloud environments. Our teams operate from multiple global delivery centers, supporting Zurich’s business units worldwide.

Job Title: AI / Automation SME

Location: India

About the Role:

As an AI / Automation SME, you’ll be at the core of Zurich’s “AI First” delivery — building, testing, and optimizing production-grade Artificial Intelligence and Generative AI solutions. You will develop GenAI and agentic capabilities (LLMs, RAG, prompt engineering) that accelerate development, automate manual effort, and improve troubleshooting — delivering reliable, secure, observable, responsible, and compliant solutions that drive data-driven decisions and continuous improvement.

Key Responsibilities:

• Develop, configure, and maintain production-grade AI / Generative AI solutions (LLM applications, RAG pipelines, agentic workflows) across the global organization (Group and BU levels).
• Build RAG and retrieval pipelines with attention to retrieval quality (chunking, embeddings, reranking) and measure it, not just assemble it.
• Choose the simplest solution that meets the need — knowing when a single well-designed agent or pipeline beats a complex multi-agent system.
• Perform prompt engineering, testing, evaluation, troubleshooting, and optimization of AI solutions for accuracy, latency, and cost; build eval sets and catch hallucinations.
• Instrument solutions with observability/tracing (e.g., Langfuse / OpenTelemetry) and apply basic AI security practices: prompt-injection awareness, safe tool use, secrets and PII handling.
• Work closely with the Lead AI / Automation SME, architects, business analysts, and stakeholders to translate requirements into technical deliverables.
• Implement integrations between AI solutions and enterprise systems like Databricks, leveraging APIs and appropriate middleware.
• Building, operating, and continuously improving the systems in scope while leveraging AI capabilities to accelerate development, improve troubleshooting / enhance governance outcomes.
• Reduce manual remediation effort by identifying recurring patterns and optimization opportunities in the scope using AI-supported insights.
• Contribute to the service’s AI adoption goals and deliver measurable outcomes.
• Document solution designs, model/agent logic, and workflows clearly and comprehensively; use ADO, JIRA and SNOW to manage work and enable smooth releases.
• Ensure all solutions comply with Zurich’s quality, security, data privacy, and responsible-AI standards.

Qualifications:

• 4–8 years building software / AI solutions, including 2+ years hands-on with Generative AI in production (LLMs, RAG, prompt engineering); agentic experience a strong plus.
• Proven track record of integrating solutions with enterprise applications/platforms (like Databricks) via ADO and APIs.
• Strong analytical and problem-solving skills, with attention to detail and a focus on evaluation and impact analysis.
• Demonstrated capability in supporting operational activities and continuous improvement.
• Collaborative mindset and effective communicator, fluent in English.

Must have Skills (Top 5 skills):

• Hands-on Generative AI development at production quality (LLMs, RAG, prompt engineering, agent frameworks such as LangChain / LangGraph / CrewAI or similar).
• Python and solid software engineering / testing fundamentals (including testing non-deterministic AI outputs).
• AI evaluation & observability: eval sets, tracing (e.g., Langfuse / OpenTelemetry), and cost/latency/hallucination awareness.
• **Basic AI sec…