onsite
Senior AI Engineer - Applied Agentic AI - WTS Group
AI Engineer
Senior AI Engineer responsible for designing, optimizing, and operating LLM‑based applications and AI agents on the plAIground platform, implementing RAG pipelines, and collaborating with backend, frontend, and product teams.
About the role
Key Responsibilities
- Design, develop, and maintain large‑language‑model (LLM) applications and autonomous AI agents on the internal plAIground platform.
- Architect and implement Retrieval‑Augmented Generation (RAG) pipelines, including data ingestion, chunking strategies, retrieval optimization, and multi‑source re‑ranking.
- Leverage Python expertise and LLM orchestration frameworks such as LangGraph, Semantic Kernel, and CrewAI to build scalable, production‑ready solutions.
- Collaborate closely with backend, frontend, and product teams to integrate AI capabilities into end‑user features.
- Monitor performance, conduct profiling, and continuously improve model efficiency, latency, and cost.
Requirements
- Strong professional experience in Python development for AI/ML workloads.
- Deep understanding of large language models, prompt engineering, and RAG architectures.
- Hands‑on experience with LLM orchestration tools (e.g., LangGraph, Semantic Kernel, CrewAI) and vector databases.
- Proven ability to design data ingestion pipelines, chunking, and retrieval optimization for multi‑source data.
- Excellent teamwork and communication skills to work across engineering and product disciplines.