Software Engineer – AI/LLM Applications

Company

Brief Description

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.

Role Overview

Global Rescue is seeking a versatile and driven Software Engineer – AI/LLM Applications with a strong focus on building AI-enabled enterprise software solutions. This role is intended for a strong software engineer who has hands-on experience with enterprise application development and has moved into AI-first development using LLMs, agents, automation, and modern AI engineering tools.

This role focuses on building production-ready features, AI agents, assistants, and intelligent workflow systems that can use tools, call APIs, integrate with enterprise applications, reason over business context, and support both short-running and long-running business processes.

This is primarily a software engineering role focused on building AI-enabled product features within enterprise systems, not a pure data science, ML research, or AI scripting-only position.

The role involves integrating third-party LLMs such as OpenAI, Google Gemini, Claude, and other model providers into enterprise systems, while developing AI-powered features such as chatbots, assistants, Q&A systems, contextual search, RAG pipelines, workflow automation, and agentic business processes.

You will work on prompt engineering, embedding-based customization, lightweight fine-tuning, structured outputs, tool-calling, agent evaluation, validation flows, and modern agent frameworks such as Pydantic AI, Claude Agent SDK, OpenAI Agents SDK, LangGraph, or similar tools.

The role may also involve developing capabilities in speech-to-text, text-to-speech, audio classification, sentiment analysis, intent recognition, and emotion detection to support multimodal AI experiences. Strong software engineering fundamentals, Python skills, applied AI/LLM knowledge, and experience integrating AI into real-world production applications are essential.

Responsibilities

• Build, enhance, and integrate AI/LLM capabilities into enterprise applications and business systems built on any of the following technology stacks: Java, Spring Boot, Kotlin, .NET, Dynamics 365, or similar platforms, ensuring AI-enabled features are developed with strong software engineering fundamentals, clean architecture, reliable integrations, scalability, maintainability, and modern AI-first development practices.
• Integrate, leverage, and customize LLMs such as OpenAI, Gemini, Claude, and similar providers through APIs to enhance enterprise product features including chatbots, Q&A systems, contextual search, workflow automation, and AI-assisted user experiences.
• Design, build, and deploy practical agentic AI systems that work within existing enterprise applications and are capable of handling short-running task execution as well as long-running, multi-step workflows involving APIs, databases, vector stores, and business systems.
• Design and implement prompt engineering strategies, structured outputs, tool-calling patterns, lightweight model customization techniques, and validation flows to adapt AI capabilities to business-specific software use cases.
• Build retrieval-augmented generation pipelines by integrating LLMs with vector stores such as FAISS, Pinecone, Qdrant, or similar platforms for reliable and dynamic knowledge grounding.
• Develop backend services, APIs, and integration components required to connect AI/LLM features with enterprise applications, databases, internal tools, and third-party systems.
• Develop AI components for speech processing, including speech-to-text, text-to-speech, audio classification, and voice-based workflows using tools and services such as Whisper, Google Speech APIs, Azure Speech, or similar platforms.
• Implement NLP and classification features such as sentiment analysis, intent recognition, entity extraction, summarization, and emotion detection using open-source libraries, cloud services, or third-party APIs.
• Follow an AI-first development approach by actively using modern AI coding assistants, LLM-based development tools, automation techniques, and rapid prototyping to improve productivity, code quality, debugging, documentation, and delivery speed.
• Collaborate with product, engineering, and business teams to identify opportunities where AI can improve workflows, automate repetitive tasks, enhance user experience, or support better decision-making.
• Develop clean, efficient, maintainable, and testable code using Python and/or relevant enterprise technology stacks, and actively participate in peer reviews, debugging, testing, CI/CD workflows, and MLOps/LLMOps-related activities.
• Monitor AI model performance, response quality, latency, token usage, and cost in production, and apply best practices for scalability, reliability, security, and cost-efficiency.
• Implement AI safety, validation, guardrails, error handling, fallback behavior, and evaluation checks to improve reliability of LLM-based workflows.
• Document workflows, implementation details, prompt strategies, model behavior, evaluation results, and integration patterns for cross-functional collaboration and long-term maintainability.
  
  

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
• 4+ years of software development experience, including 2–3 years of hands-on experience building enterprise applications using any of the following technology stacks: .NET, Java, Spring Boot, Dynamics 365, or similar systems, along with 1–2 recent years of hands-on AI/LLM application development, preferably within an enterprise stack or using Python.
• Practical experience integrating LLMs through APIs such as OpenAI, Gemini, Claude, or similar providers.
• Strong understanding of prompt engineering, embeddings, model customization techniques, and basic LLM evaluation approaches.
• Experience building AI agents, agentic workflows, or tool-using LLM applications that interact with APIs, databases, vector stores, and enterprise systems.
• Familiarity with modern AI/agent frameworks 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 audio-based AI applications such as speech-to-text, text-to-speech, audio classification, and emotion or sentiment detection.
• Experience with REST APIs, FastAPI or similar backend frameworks, microservices, Docker, cloud platforms such as AWS, and GPU-enabled environments.
• Understanding of production concerns for LLM-based and agentic systems, including observability, latency, cost management, error handling, permissions, prompt/version management, security, and scalable deployment.
• Strong problem-solving skills, software design fundamentals, ownership mindset, and ability to work collaboratively in a team environment.
  
  

LOCATION: Islamabad

COMPENSATION: Based on experience + bonus + benefits