Overview
Skills
Job Details
About the Role
We are seeking a highly skilled LLM (Large Language Model) Engineer to design, develop, and optimize advanced AI-driven solutions. The ideal candidate will have deep expertise in integrating and fine-tuning LLMs using APIs, building scalable pipelines, and leveraging modern tools and frameworks for applied AI. This role requires hands-on experience with vector databases, orchestration frameworks, and deployment within agile development environments.
Key Responsibilities
Design, develop, and integrate LLM-based applications using APIs and custom tool use.
Build and maintain MCP server and pipelines to support large-scale model deployment.
Develop conversational and agentic workflows using LangGraph and DSPy.
Implement and optimize vector search with Qdrant, Milvus, or PgVector for efficient retrieval-augmented generation (RAG) solutions.
Collaborate with data scientists, engineers, and product teams to deliver scalable AI features.
Ensure CI/CD and DevOps best practices using Azure DevOps.
Work in an Agile development environment, contributing to sprint planning, standups, and retrospectives.
Research and evaluate emerging tools, libraries, and best practices to continuously improve the LLM ecosystem.
Required Skills & Qualifications
Strong proficiency with LLM APIs (OpenAI, Anthropic, Hugging Face, etc.).
Hands-on experience with LangGraph and/or DSPy.
Knowledge of MCP server setup and integration.
Experience with vector databases (Qdrant, Milvus, PgVector).
Familiarity with tool use frameworks for LLM agents.
Solid understanding of Azure DevOps pipelines, CI/CD, and deployment practices.
Experience working in Agile teams.
Strong problem-solving skills and ability to design efficient, scalable systems.
Preferred Qualifications
Bachelor s or Master s degree in Computer Science, AI/ML, Data Science, or related field.
Experience with cloud-based AI/ML deployments (Azure, AWS, or Google Cloud Platform).
Contributions to open-source LLM or vector database projects.
Familiarity with retrieval-augmented generation (RAG) architectures.
Strong background in Python and modern AI/ML frameworks.