Senior AI Engineer (Agentic)

Job Description

• Research, design, and optimize AI Agent architectures: planning, tool-use / function calling, memory, and multi-agent orchestration for RAGEngine and GreenNode's AI products.
• Build and optimize end-to-end Agentic RAG pipelines: ingestion, chunking, embedding, hybrid retrieval (dense/sparse), reranking, query rewriting/decomposition, and iterative & self-reflective retrieval.
• Design evaluation systems for agent and RAG quality: faithfulness, answer relevancy, retrieval precision/recall; build benchmarks and automated evaluation processes (LLM-as-a-judge, RAGAS, or equivalent).
• Jointly optimize quality, latency, and cost: semantic caching, model routing, prompt optimization, and context management/compression.
• Collaborate with product and infrastructure teams to bring research results into production on GreenNode's self-hosted model platform.
• Keep up with new research and standards (agent frameworks, MCP, A2A, deep research patterns, etc.) and propose applying them to products.

Requirements

• 4+ years (Senior) of AI/ML Engineering experience, including at least 1–2 years working directly with LLM applications.
• Proficient in Python; experience with agent/RAG frameworks (LangChain/LangGraph, LlamaIndex, AutoGen, CrewAI, etc.) or building agent systems from scratch.
• Deep practical understanding of LLMs: prompt engineering, function calling, structured output, and context window management.
• Experience with embeddings and vector databases (Milvus, Qdrant, Weaviate, pgvector, etc.), and search/IR techniques: BM25, hybrid search, and rerankers (cross-encoders).
• Has taken LLM systems to production: API design, monitoring, and observability/tracing (Langfuse, OpenTelemetry, or equivalent).
• Good English reading comprehension of technical documents and papers.