Lead AI Engineer

• 2+ years of experience in AI, NLP, or LLM-based applications.

• 5+ years of experience with API development and consumption (REST, JSON, OAuth, etc.).

• Hands-on experience working with at least one of the major LLMs: GPT, Claude, Gemini, or LLaMA.

• Practical experience with RAG architecture and vector databases (e.g., ChromaDB, Pinecone, Weaviate).

• Strong backend development skills, preferably in PHP (alternatively Python or Java).

• Familiarity with LangChain, LangGraph, and LangSmith.

• Solid understanding of MCP (Model Context Protocol) and structured prompt design.

• Experience deploying and operating AI systems on AWS, Azure, or on-prem environments.

• Familiarity with containerization and orchestration tools (e.g., Docker, Kubernetes).

• Experience with open-source LLM frameworks or fine-tuning custom models.

• Experience integrating speech-to-text (STT) and text-to-speech (TTS) engines (e.g., Whisper, Amazon Polly, Google Speech, Azure Speech).

• Exposure to DevOps, CI/CD pipelines, or MLOps platforms.

• Architect and develop AI-driven solutions using LLMs including GPT, Claude, Gemini, and LLaMA.

• Build and maintain RAG pipelines with integration to a vector database for semantic search and retrieval.

• Design and manage workflows using LangChain, LangGraph, and LangSmith.

• Apply Model Context Protocol (MCP) for structured and reusable prompt engineering.

• Develop backend services primarily in PHP (preferred), or alternatively in Python or Java.

• Design, consume, and maintain RESTful and external APIs, ensuring secure and efficient integrations.

• Deploy AI services across AWS, Azure, or on-prem infrastructure as required.

• Monitor, evaluate, and optimize LLM usage and performance in real-world applications.

• Lead and mentor engineers across AI/ML development efforts.

Randstad