Senior AI Architect: Agentic Systems & RAG Pipelines

Tkxel; Lahore; On-site; PKR 2,000,000 - 4,000,000; Full time

Job summary

Tkxel seeks an Expert AI Engineer to own design, architecture, and deployment of Agentic AI systems for a bilingual enterprise knowledge platform. You will drive autonomous, multi-agent workflows on top of production-grade RAG pipelines, with end-to-end ownership of architecture, quality, and performance.

Responsibilities cover architecture of agentic systems, orchestration, and robust workflow layers, including integration with enterprise APIs, background processing, and grounded generation

Qualifications

• Deep, demonstrated expertise in agentic AI and LLM-based applications, with a track record of production systems.
• Expert Python proficiency and a strong software engineering foundation, including production deployment and system design.
• Proven experience architecting agentic systems with planning, tool use, orchestration, and multi-agent coordination.
• Hands-on experience with agent frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, or CrewAI.
• Strong command of agent state management, tool/function calling, and MCP standards.
• Experience designing workflow orchestration systems with DAG/state-machine execution and durable state.
• Experience building connectors to enterprise systems and APIs with OAuth and service accounts.
• Production experience with background job and scheduling infra (Celery, Airflow, Prefect, Temporal).
• Hands-on with vector databases (Milvus, FAISS, Qdrant, pgvector) and lexical search (BM25, Elasticsearch).
• Expert command of retrieval techniques, including dense/sparse/hybrid and reranking.
• Advanced prompt engineering and grounding techniques for large language models.
• Track record deploying and scaling production-ready agentic AI pipelines.
• Strong grasp of RAG and agent evaluation methodologies; define quality standards.

Responsibilities

• Architect Agentic systems with query planning, reasoning, memory, tool use, and multi-step execution.
• Define orchestration patterns coordinating agents, retrieval, tools, and LLM calls into pipelines.
• Design robust single- and multi-agent architectures with state management and guardrails.
• Architect the workflow layer with versioned, durable, retryable steps and human-in-the-loop checks.
• Design connectors and integration layers for enterprise content sources and APIs.
• Own background processing: scheduled ingestion, index/embedding refresh, queues, and retries.
• Own and optimize the RAG layer: chunking, embedding, retrieval, reranking, grounded generation.
• Implement/dial in dense, sparse, hybrid, and metadata-based retrieval using vector DBs and BM25.
• Establish prompting, grounding, and verification to ensure citation-backed responses.
• Define evaluation frameworks and quality gates; drive performance improvements.

Skills

Python proficiency

Agentic AI

System design

Production deployment

LangGraph

LangChain

LlamaIndex

AutoGen

CrewAI

Tools

LangGraph

LangChain

LlamaIndex

AutoGen

CrewAI

Job description

Tkxel seeks an Expert AI Engineer to own design, architecture, and deployment of Agentic AI systems for a bilingual enterprise knowledge platform. You will drive autonomous, multi-agent workflows on top of production-grade RAG pipelines, with end-to-end ownership of architecture, quality, and performance.

Responsibilities cover architecture of agentic systems, orchestration, and robust workflow layers, including integration with enterprise APIs, background processing, and grounded generation