AI Product, Senior Engineer (LLM & Agentic AI)

Nabeh, a subsidiary of Master Works, delivers AI-powered solutions that help organizations automate operations, boost efficiency, and drive innovation. Its expertise spans computer vision, LLM applications, speech-to-text, data intelligence, and low-code AI solutions.

Nabeh is looking for an AI Product Engineer (LLM & Agentic AI) to develop and deploy production-ready AI applications using LLMs, RAG, and Agentic AI, contributing to Nabeh's AI products and enterprise solutions.

Key Responsibilities

LLM Application Development

•  Design and develop enterprise AI applications powered by proprietary and open-source LLMs.

•  Build advanced RAG pipelines for ingestion, chunking, embeddings, indexing, retrieval, reranking, and grounded responses.

•  Develop AI agents capable of tool calling, multi-step task execution, and integration with enterprise systems.

•  Implement multi-agent and workflow-based AI solutions with reliable execution and error handling.

•  Develop structured output pipelines, prompt templates, and context-management strategies.

•  Build conversational AI capabilities supporting multilingual interactions, particularly Arabic and English.

LLM Platform & Inference Engineering

•  Integrate multiple AI providers through OpenAI-compatible APIs.

•  Deploy and serve open-source LLMs using inference frameworks such as vLLM.

•  Work with cloud-hosted and on-premises inference infrastructure.

•  Optimize inference latency, throughput, concurrency, token usage, and cost.

•  Implement model routing, fallback mechanisms, request logging, usage tracking, and API integration.

•  Support deployments on NVIDIA GPUs and other AI accelerators, including Qualcomm Cloud AI platforms.

Production AI Engineering

•  Build reliable backend services using Python and frameworks such as FastAPI.

•  Design RESTful APIs, asynchronous workers, streaming responses, and event-driven integrations.

•  Work with SQL and vector databases such as PostgreSQL, pgvector, Qdrant, or Milvus.

•  Integrate AI services into enterprise workflows, knowledge systems, and third-party applications.

•  Containerize applications using Docker and support Kubernetes-based deployments.

•  Implement observability, automated testing, CI/CD, and production monitoring.

AI Quality, Evaluation & Governance

•  Develop evaluation pipelines measuring answer quality, grounding, hallucination rates, latency, and cost.

•  Implement prompt-injection defenses, access controls, PII protection, and content guardrails.

•  Support secure AI deployments aligned with enterprise privacy requirements.

•  Evaluate and benchmark new LLMs, embeddings, reranking models, and inference approaches.

•  Troubleshoot production issues across application, model, and inference layers.

Product Ownership & Collaboration

•  Collaborate with product managers to convert requirements into functional AI capabilities.

•  Own assigned features from technical design and implementation to deployment and monitoring.

•  Deliver maintainable, reusable components rather than isolated POCs.

•  Participate in architecture reviews, technical documentation, code reviews, and product demonstrations.