Senior AI Engineer

Sapiens International; Bengaluru; On-site; INR 400,000 - 700,000; Full time

Job summary

Sapiens International is hiring for a role building agentic AI systems that support complex insurance software implementations. You will craft multi-step reasoning, design long-horizon workflows, and deliver robust RAG pipelines across data ingestions and grounding.

The role emphasizes production-grade Python, LangGraph orchestration, and hands-on use of Claude and Azure AI Foundry. Expect collaboration across enterprise cloud AI platforms, strong testing and CI/CD practices, and a focus on

Qualifications

• Proven track record shipping production agentic AI systems.
• Hands-on experience with LangGraph or similar orchestration.
• Deep Python proficiency; production-ready code.
• Experience designing end-to-end RAG systems.
• Daily use of Claude and Claude Code.
• Experience deploying agents on Azure AI Foundry.
• Understanding LLM behavior and evaluation methods.
• Experience with MCP-based interoperability patterns.

Responsibilities

• Design and implement agentic systems with multi-step reasoning and workflow execution.
• Build stateful workflows and reusable orchestration patterns.
• Engineer for long-horizon reliability and robust tool use.
• Develop end-to-end RAG pipelines across ingestion to grounding.
• Ensure observability, safety controls, and quality checks in production.

Skills

LangGraph

Python

Claude API

Claude Code

Azure AI Foundry

CI/CD

Observability

MCP tooling

Vector databases

RAG systems

Tools

LangGraph

Azure AI Foundry

Claude (Anthropic API)

Claude Code

Pinecone

Weaviate

Azure AI Search

OpenSearch

Job description

Insurance software implementations are among the most complex, document-heavy, and process-intensive programmes in enterprise technology. A single implementation can involve thousands of configuration decisions, hundreds of requirement documents, and years of delivery time. Sapiens is rebuilding how that work gets done — using production-grade AI agents that operate across the full implementation lifecycle, from pre-sales and scoping through to configuration, testing, and go-live.

Work You'll Do

• Design and implement agentic systems capable of multi-step reasoning, planning, tool use, and workflow execution against complex, document-intensive implementation processes
• Build stateful workflows using LangGraph or equivalent — including branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns
• Engineer for long-horizon reliability — multi-step task completion, recovery from compounding errors, planning under uncertainty, and robust tool use when individual steps fail
• Build the reasoning behind high-stakes implementation decisions — criteria-grounded outputs, structured review patterns, and auditable rationales that delivery consultants can act on and defend
• Develop end-to-end RAG pipelines: ingestion, chunking, embeddings, vector and hybrid retrieval, reranking, contextual compression, and grounding strategies
• Engineer memory and context management — conversational state, persistent memory, retrieval-aware context assembly, and token-efficient context selection
• Apply MCP-style tool and context interfaces so agents access the right information at the right time across enterprise knowledge repositories, document sources, and structured configuration data

Reliability, evaluation & safety

• Implement observability and tracing for prompts, tool calls, retrieval quality, agent traces, failures, drift, latency, and production behaviour
• Apply guardrails, safety controls, and failure-handling to reduce hallucinations in agents whose outputs practitioners act on directly in live client settings
• Evaluate agents at trajectory and task level — multi-step task success, failure-mode and regression analysis, sandboxed test environments — alongside retrieval and generation quality metrics, automated checks, and human review

Integration & production craft

• Build integrations with internal and external tools, APIs, enterprise systems, databases, and model providers so agents operate reliably within real delivery workflows
• Deliver production-quality Python code with strong practices in testing, CI/CD, logging, versioning, and documentation; make architecture decisions that balance quality, reliability, latency, cost, and model risk
• Translate ambiguous, high-complexity implementation processes into robust system logic and reusable AI patterns; stay current with advances in agentic systems and translate research into practical engineering decisions

Required Qualifications

• Demonstrated depth building and shipping production agentic AI systems — we weigh shipped systems over years in a title
• Strong, hands-on experience with LangGraph or equivalent agentic orchestration frameworks, including custom orchestration
• Deep proficiency in Python — clean, testable, production-ready code
• Experience designing and optimising end-to-end RAG systems: indexing, retrieval, reranking, grounding, and evaluation
• Daily working proficiency with Claude (Anthropic API) and Claude Code — you use these tools every day, not occasionally
• Experience building and deploying agents on Azure AI Foundry or an equivalent enterprise cloud AI platform
• Practical understanding of LLM behaviour — strengths, limitations, hallucination risks, reasoning constraints, and the evaluation methods used to measure them
• Experience evaluating and debugging agent behaviour at trajectory and task level, not just output quality
• Hands-on experience with MCP-based interoperability patterns and tool-calling agent design
• Modern software practices: testing, CI/CD, observability, tracing, and debugging for LLM-based systems in production

Preferred Qualifications

• Experience of 4+ years
• Experience with multi-agent orchestration and agent collaboration patterns
• Familiarity with vector databases — Pinecone, Weaviate, Azure AI Search, OpenSearch
• Experience building agents that process complex, unstructured document types — contracts, RFPs, configuration files, regulatory documents
• Exposure to model adaptation techniques such as LoRA or QLoRA
• Prior work in insurance, financial services, or enterprise SaaS implementation environments
• Demonstrated habit of staying current with AI research, benchmarks, and emerging engineering patterns

About Us:

Sapiens International Corporation N.V. is a global leader of AI-centric, SaaS-based insurance software, delivering hyper-relevant experiences that are efficient, compliant, and innovative. With agile intelligence, Sapiens’ solutions turn real-time data and human insight into precise action at every moment, across every risk.

The Sapiens platform includes agentic workflows accelerating every capability across policy, underwriting, claims, reinsurance, decisioning, finance and compliance.

With more than 600 insurers in over 30 countries running on Sapiens, our deep industry expertise is the foundation of our long‑term relationships, from initial implementation through to modernisation and market transformation.

Sapiens is headquartered in London, serving customers in property and casualty, life, reinsurance, specialty, and workers’ compensation from offices across North America, Europe, Asia Pacific and the Middle East including Israel where the company was founded.

We Are

Sapiens International Corporation N.V. is a global leader of AI-centric, SaaS-based insurance software, delivering hyper-relevant experiences that are efficient, compliant, and innovative. With agile intelligence, Sapiens' solutions turn real-time data and human insight into precise action at every moment, across every risk.

The Sapiens platform includes agentic workflows accelerating every capability across policy, underwriting, claims, reinsurance, decisioning, and finance and compliance.

With more than 600 insurers in over 30 countries running on Sapiens, our deep industry expertise is the foundation of our long‑term relationships, from initial implementation through to modernization and market transformation.

Sapiens is headquartered in London, serving customers in property and casualty, life, reinsurance, specialty, and workers’ compensation from offices across North America, Europe, the Middle East, and Asia Pacific.