Generative AI/LLM Engineer
Overview:
In this role you will design, build, and deploy enterprise AI solutions powered by LLMs to automate processes, improve user experiences, and drive measurable business outcomes. You will work with cross-functional teams to architect scalable AI systems, including agents, RAG platforms, and multimodal capabilities. The role focuses on delivering production-ready AI solutions that balance performance, cost, and governance. You will stay at the forefront of AI tech, shaping reusable components and standards that scale across the organization.
Responsibilities:
- Design, develop, and deploy AI agents powered by Large Language Models (LLMs)
- Build and optimize Retrieval-Augmented Generation (RAG) solutions with vector search and semantic retrieval
- Develop AI-powered apps leveraging text, voice, image, and document intelligence
- Create scalable APIs, microservices, and backend services for AI workloads
- Integrate AI platforms with enterprise systems and automation frameworks
- Implement workflow automation and orchestration to streamline business processes
- Evaluate and improve model accuracy, performance, reliability, and cost efficiency
- Collaborate with product, engineering, operations, and business stakeholders
- Apply prompt engineering best practices to enhance outputs and user experiences
- Ensure security, privacy, governance, and responsible AI compliance
- Contribute to architecture standards, reusable components, and AI engineering best practices
- Stay current with emerging AI technologies and propose innovative approaches
Key requirements:
Bachelor's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Software Engineering, or related field 5+ years of professional software development experience, including PythonHands-on experience with leading LLM providers (OpenAI, Anthropic, Meta, Mistral, or similar) Strong prompt engineering, model evaluation, and AI app development skills Experience designing and implementing RAG architectures Experience with vector databases and semantic search (Pinecone, Weaviate, Chroma, Milvus, or equivalent) Experience building REST APIs, microservices, and scalable cloud apps Knowledge of AI agent frameworks (LangChain, LlamaIndex, CrewAI, AutoGen, or similar) Experience deploying apps in AWS, Azure, or Google Cloud Understanding of software design patterns, testing, and CI/CDStrong communication and collaboration skillscollaborationcross-functional communicationproblem-solving Python developmentLLM integrationRAG architectures