AI Engineer

We are looking for an Expert AI Engineer to lead the design, architecture, and deployment of advanced agentic AI systems for a bilingual enterprise knowledge platform powered by large language models. This role involves setting the technical vision for autonomous, multi-agent, and multi-step workflows that incorporate planning, reasoning, memory, and tool integration. You will work on production-grade Retrieval-Augmented Generation (RAG) pipelines and the supporting workflow, integration, and background processing layers. This position requires full end-to-end ownership of system architecture, quality, and performance.

Key Responsibilities

- Architect agentic AI systems that include query planning, reasoning, memory management, tool usage, and multi-step task execution.
- Define orchestration patterns to coordinate agents, retrieval mechanisms, tools, and LLM calls into reliable and observable autonomous pipelines.
- Design robust architectures for both single-agent and multi-agent systems, incorporating state management, control flow, error recovery, and guardrails.
- Develop the workflow layer with composable, versioned workflows that combine deterministic steps, agentic branches, conditional routing, and human-in-the-loop checkpoints, ensuring durable state, checkpointing, and retries.
- Design and implement connector and integration layers for enterprise content sources and APIs, addressing authentication, incremental synchronization, content normalization, and permission-aware retrieval.
- Own the background processing infrastructure, including scheduled data ingestion, index and embedding refresh, job queuing, concurrency control, failure recovery, and content freshness monitoring.
- Manage and optimize the underlying RAG layer, covering chunking, embedding, retrieval, reranking, and grounded generation.
- Implement and fine-tune dense, sparse, hybrid, and metadata-based retrieval methods using vector databases and BM25.
- Establish prompting, grounding, and verification strategies to ensure responses are accurate and citation-backed.
- Define evaluation frameworks and quality gates to drive continuous improvement in task success, relevance, latency, and reliability.

Required Qualifications

- Proven expertise in agentic AI and large language model-based applications, with a strong track record of deploying production systems.
- Expert-level proficiency in Python and solid software engineering skills, including system design and production deployment.
- Demonstrated experience architecting agentic systems with planning, tool integration, orchestration, and multi-agent coordination.
- Hands-on experience with agent frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, or CrewAI.
- Strong knowledge of agent state management, tool/function calling, and standards like the Model Context Protocol (MCP).
- Experience designing workflow orchestration systems, including DAG or state-machine execution, durable state management, retry semantics, and idempotent step design.
- Practical experience building connectors and integrations with enterprise systems and third-party APIs, including OAuth and service-account authentication, rate limiting, and permission-aware synchronization.
- Production experience with background job and scheduling infrastructure such as Celery, Airflow, Prefect, or Temporal, including scheduled ingestion and failure recovery.
- Hands-on experience with vector databases like Milvus, FAISS, Qdrant, or pgvector, as well as lexical search technologies such as BM25 and Elasticsearch.
- Expert understanding of retrieval techniques, including dense, sparse, hybrid, and filtered search, along with reranking methods.
- Advanced skills in prompt engineering and grounding techniques for large language models.
- Proven ability to deploy, scale, and optimize production-ready agentic AI pipelines.
- Strong grasp of RAG and agent evaluation methodologies, with experience defining quality standards.

This role offers the opportunity to take full ownership of cutting-edge AI systems that drive enterprise knowledge platforms, working at the intersection of advanced AI research and practical, scalable deployment. If you are passionate about architecting autonomous AI workflows and delivering high-quality, reliable AI-driven solutions, this position is an excellent fit.