We are seeking a skilled AI Engineer to design and develop advanced Large Language Model (LLM)-powered Retrieval-Augmented Generation (RAG) systems tailored for enterprise document management. The role involves building intelligent AI agents capable of analyzing insurance and reinsurance submissions to identify next actions, missing information, and relevant documents. The ideal candidate will have hands-on experience creating agentic workflows and multi-agent systems, integrating with various databases and APIs, and deploying production-grade generative AI applications within enterprise environments.
Key Responsibilities
- Design and develop LLM-powered RAG systems that leverage enterprise documents to create searchable knowledge bases.
- Build AI agents that analyze insurance/reinsurance submissions to determine required next steps, identify missing information, and locate relevant documents.
- Develop agentic workflows using LLM tool and function calling, employing frameworks such as LangGraph, LangChain, LlamaIndex, and Semantic Kernel.
- Create tools enabling AI agents to interact seamlessly with vector databases, SQL and enterprise databases, APIs, web search, and internal applications.
- Architect multi-agent systems where AI agents communicate, delegate tasks, and collaborate effectively.
- Implement document ingestion processes including chunking, embeddings, vector search, hybrid search, and reranking techniques.
- Integrate commercial and open-source LLMs and embedding models to enhance system capabilities.
- Develop natural-language database querying and Text-to-SQL functionalities with robust security and control measures.
- Build feedback and evaluation mechanisms to support continuous improvement and self-learning of AI systems.
- Implement monitoring, logging, evaluation, hallucination and grounding checks, along with AI security and guardrails.
- Deploy and integrate AI services with existing enterprise applications and databases to ensure smooth operation.
Required Qualifications
- Strong proficiency in Python and backend development.
- Practical experience working with LLMs, RAG systems, vector databases, and AI agents.
- Familiarity with frameworks such as LangGraph, LangChain, LlamaIndex, or similar tools.
- Experience in tool calling, function calling, agent orchestration, and building multi-agent systems.
- Solid skills in SQL, database management, and API integration.
- Experience with relational databases such as PostgreSQL, SQL Server, Oracle, as well as vector databases.
- Exposure to cloud platforms including Azure, AWS, or Google Cloud Platform.
- Proven track record of building production-grade generative AI applications rather than prototypes.
- Knowledge of insurance or reinsurance domains, underwriting, submissions, and related workflows is highly advantageous.
Location and Working Hours
The position is based in DHA Phase 3, Lahore, with working hours from 1 PM to 10 PM.
This role offers the opportunity to work at the forefront of AI innovation within the insurance sector, contributing to cutting-edge solutions that enhance operational efficiency and decision-making.