Senior AI Agents Programmer

Kanz; Jeddah; On-site; SAR 180,000 - 340,000; Full time

Job summary

Kanz in Jeddah is seeking an experienced AI/ML engineer to ship agent workflows in production and optimize performance. You will iterate to improve task success, reduce latency, and implement guardrails for safe, scalable AI systems.

The role requires deep proficiency in Python, building LLM-based applications, and familiarity with agent architectures, evaluation, and deployment pipelines. You will work with LangChain, LlamaIndex, LangSmith, and vector databases in a cloud environment,

Qualifications

• Proficiency in Python and software engineering fundamentals.
• Experience building LLM-based applications.
• Understanding of agent architectures (planning, tools, memory).
• Familiarity with evaluation, testing, and monitoring for AI systems.
• Experience with APIs, distributed systems, and deployment pipelines.
• Python LLM frameworks such as LangChain and LlamaIndex.
• Knowledge of agent frameworks and tool use.
• Prompting and function calling.
• Experience with vector databases (e.g., Pinecone/FAISS).
• Experience with evaluation/observability tools like LangSmith.
• Familiarity with APIs and microservices.
• CI/CD and cloud deployment.
• Strong problem-solving and systems thinking.
• Attention to detail and reliability.

Responsibilities

• Ship working agent workflows in production.
• Improve task success rate through iteration.
• Reduce latency and inference costs.
• Implement guardrails and safety evaluations.
• Monitor and optimize agent performance continuously.

Skills

Python

LLM-based applications

Agent architectures

Evaluation/observability

APIs & microservices

CI/CD

Cloud deployment

Problem solving

Attention to detail

Reliability

Tools

LangChain

LlamaIndex

LangSmith

Pinecone

FAISS

Job description

Job Duties and Responsibilities

• Ship working agent workflows in production
• Improve task success rate through iteration
• Reduce latency and inference costs
• Implement guardrails and safety evaluations
• Monitor and optimize agent performance continuously

Qualifications Required

• Proficiency in Python and software engineering fundamentals
• Experience building LLM-based applications
• Understanding of agent architectures (planning, tools, memory)
• Familiarity with evaluation, testing, and monitoring for AI systems
• Experience with APIs, distributed systems, and deployment pipelines
• Python LLM frameworks (LangChain/LlamaIndex)
• Agent frameworks and tool use
• Prompting and function calling
• Vector databases (e.g., Pinecone/FAISS)
• Evaluation/observability (e.g., LangSmith)
• APIs and microservices
• CI/CD and cloud deployment
• Problem-solving and systems thinking
• Attention to detail and reliability