## Description COMPANY Global Rescue is the world’s leading membership organization providing integrated medical, security, intelligence and crisis response services to consumers, enterprises and governments. Founded in 2004 Global Rescue’s unique operational model provides best-in-class services that identify, monitor, and respond to threats and emergencies. For more information, please see [www.globalrescue.com](http://www.globalrescue.com/). ROLE OVERVIEW Global Rescue is seeking a motivated and capable Associate Software Engineer – AI/LLM Applications with a strong interest in agentic AI engineering, LLM applications, and applied machine learning. This role focuses on contributing to real-world AI agents, assistants, and intelligent workflow systems that can use tools, call APIs, retrieve information, reason over enterprise context, and execute well-defined business workflows. This is primarily a software engineering role focused on building AI-enabled product features, not a pure data science or research-only position. The role involves working with third-party LLMs such as OpenAI, Google Gemini, Claude, and other model providers to develop AI-powered features including chatbots, assistants, Q&A systems, contextual search, RAG pipelines, and agentic automation workflows. You will work on prompt engineering, embedding-based customization, structured outputs, tool-calling, agent evaluation harnesses, and modern agent frameworks such as Pydantic AI, Claude Agent SDK, OpenAI Agents SDK, or similar tools. The role also involves developing capabilities in speech-to-text, text-to-speech, audio classification, sentiment analysis, intent recognition, and emotion detection to support multimodal AI experiences. Strong Python fundamentals, applied problem-solving ability, and a desire to build production-grade AI applications are essential. RESPONSIBILITIES: · Integrate and customize LLMs such as OpenAI, Gemini, and Claude via APIs to develop intelligent product features including chatbots, Q&A systems, and contextual search tools. · Contribute to agentic AI systems capable of tool use, API calling, structured workflow execution, and multi-step task handling. · Apply prompt engineering strategies, structured outputs, tool-calling patterns, and embedding-based customization techniques. · Build and maintain RAG pipelines by integrating LLMs with vector stores, document processing workflows, and knowledge retrieval systems. · Develop backend AI services and integrate AI components into applications using REST APIs, FastAPI/Flask, and microservice-based patterns. · Write clean, maintainable, and testable Python code, and participate in peer reviews, debugging, testing, CI/CD workflows, and MLOps-related activities. · Follow an AI-first development approach by actively using modern AI coding assistants, LLM-based development tools, and automation techniques to improve productivity, code quality, debugging, documentation, and delivery speed. · Contribute to the implementation of AI safety, validation, guardrails, fallback behavior, and basic evaluation checks to improve reliability of LLM-based workflows. · Document workflows, implementation details, model behavior, and integration patterns for team collaboration and long-term maintainability. QUALIFICATIONS: · Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field. · 1–3 years of software development experience, with hands-on exposure to AI/LLM application development. · Practical experience integrating LLMs through APIs such as OpenAI, Gemini, Claude, or similar providers. · Understanding of prompt engineering, embeddings, model customization techniques, and basic LLM evaluation concepts. · Exposure to building AI agents, agentic workflows, or tool-using LLM applications that interact with APIs, databases, vector stores, and enterprise systems. · Familiarity with at least one modern AI/agent framework such as Pydantic AI, Claude Agent SDK, LangGraph, OpenAI Agents SDK, or similar tools. · Knowledge of RAG architectures, vector databases such as Qdrant, Pinecone, Chroma, or FAISS, and common NLP tasks including summarization, sentiment analysis, entity recognition, and intent detection. · Experience with REST APIs, FastAPI or similar backend frameworks, microservices, and cloud platforms such as AWS. · Basic understanding or hands-on exposure to enterprise application architectures and technology stacks such as .NET, Java, Spring Boot, Dynamics 365, or similar enterprise systems will be preferred. · Understanding of production concerns for LLM-based systems, including latency, cost management, error handling, logging, observability, permissions, prompt/version management, and scalable deployment. · Strong problem-solving skills, software design fundamentals, willingness to learn new technologies, and ability to work collaboratively in a team environment. LOCATION: Islamabad COMPENSATION: Based on experience + bonus + benefits