AI Engineer – Agentic Systems & RAG Platform

About the role

We are looking for an expert AI Engineer to lead the design, architecture, and deployment of agentic AI systems for a bilingual enterprise knowledge platform built on large language models. The role involves defining technical direction for autonomous, multi‑agent, multi‑step workflows that integrate planning, reasoning, memory, and tool use on top of production‑grade Retrieval‑Augmented Generation pipelines.

Key responsibilities

• Architect agentic systems with query planning, reasoning, memory, tool use and multi‑step task execution.
• Define orchestration patterns that coordinate agents, retrieval, tools and LLM calls into reliable, observable pipelines.
• Design robust single‑ and multi‑agent architectures with state management, control flow, error recovery and guardrails.
• Build composable, versioned workflow layers with deterministic steps, agentic branches, conditional routing, human‑in‑the‑loop checkpoints, durable state, checkpointing and retries.
• Develop connector and integration layers for enterprise content sources and APIs, handling authentication, incremental sync, content normalization and permission‑aware retrieval.
• Own background processing including scheduled ingestion, index and embedding refresh, job queuing, concurrency control, failure recovery and content‑freshness monitoring.
• Implement and optimise the RAG stack – chunking, embedding, retrieval, reranking and grounded generation – using dense, sparse, hybrid and metadata‑based techniques.
• Establish prompting, grounding and verification strategies to ensure accurate, citation‑backed responses.
• Define evaluation frameworks and quality gates to continuously improve task success, relevance, latency and reliability.

Required profile

• Proven deep expertise in agentic AI and LLM‑based production systems.
• Strong Python programming skills and solid software engineering foundation.
• Hands‑on experience with agent frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen or CrewAI.
• Experience designing workflow orchestration systems (DAGs, state‑machines) with durable state and idempotent steps.
• Background in building connectors and integrations to enterprise systems and third‑party APIs, including OAuth and service‑account authentication.

Required skills

• Python
• LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI
• Model Context Protocol (MCP)
• Vector databases, BM25, dense/sparse/hybrid retrieval
• RAG pipelines – chunking, embedding, retrieval, reranking, generation
• Workflow orchestration (DAG, state‑machine), durable state, retries
• OAuth, service‑account authentication, API integration, rate limiting