LLM Engineer

We are seeking a highly skilled and motivated LLM Engineer to design, build, and deploy advanced large language model (LLM) solutions that enhance procurement workflows and drive business automation. The ideal candidate will have a strong background in natural language processing, deep learning, and AI agent design, with hands-on experience fine-tuning foundation models and deploying them on Google Cloud Platform (Google Cloud Platform).

Key Responsibilities:

• AI Agent Development
  Design and implement LLM-powered AI agents that optimize and automate procurement-related tasks, ensuring reliability, explainability, and business alignment.
• Model Fine-Tuning & Optimization
  Fine-tune foundation models for domain-specific tasks, focusing on accuracy, latency, and scalability. Apply techniques such as parameter-efficient fine-tuning, prompt tuning, and adapter training.
• Pipeline Engineering
  Build and maintain robust, production-grade pipelines for data ingestion, model training, evaluation, and inference using Google Cloud Platform services and open-source tools.
• Prompt Engineering & RAG Implementation
  Leverage prompt engineering and Retrieval-Augmented Generation (RAG) to improve contextual accuracy and relevance of model outputs.
• Stakeholder Collaboration
  Work closely with procurement experts, data engineers, and business leaders to gather requirements, align goals, and deliver impactful AI solutions.
• Model Evaluation & Monitoring
  Establish evaluation metrics and monitoring tools to track model performance, accuracy, bias, and drift in real-world applications.
• Integration & Deployment
  Collaborate with cross-functional teams to integrate LLMs into existing systems, leveraging LangChain, LangGraph, and Google Cloud Platform AI tools like Vertex AI for seamless deployment.

Must-Have Qualifications:

• Master s degree in mathematics, Physics, Computer Science,
• 6 8 + years of experience in NLP, LLM development, or AI-driven automation.
• Expertise in Python and deep learning frameworks such as PyTorch and TensorFlow.
• Proficiency with LangChain, LangGraph, Hugging Face Transformers, and LLM model hubs.
• Experience fine-tuning large-scale models and optimizing for real-time inference.
• Solid understanding of vector databases, knowledge graphs, and embedding techniques.
• Strong communication skills with the ability to translate complex AI concepts to non-technical stakeholders.
• Proven experience working with Google Cloud Platform (Google Cloud Platform), especially with services like Vertex AI, BigQuery, and Cloud Functions.
• Familiarity with multi-agent systems and reinforcement learning is a strong plus.