AI / LLM Architect

Role Overview

Skyzenix Technology is pioneering intelligent enterprise systems. As our AI / LLM Architect, you will spearhead the design and deployment of cognitive agents, cutting-edge Retrieval-Augmented Generation (RAG) pipelines, and autonomous workflow automations that redefine how businesses operate.

Key Responsibilities

• Architect and productionize enterprise-grade RAG systems leveraging Pinecone, Qdrant, Chroma, and pgvector.
• Design multi-agent autonomous architectures using LangChain, LangGraph, CrewAI, and custom orchestration layers.
• Fine-tune open-source models (Llama, Mistral) for domain-specific tasks and optimize inference latency with vLLM / Ollama.
• Build robust evaluation frameworks to measure hallucination rates, retrieval precision, and semantic accuracy.
• Partner with full-stack engineers to seamlessly embed AI capabilities into web applications and mobile apps.
• Ensure strict AI data privacy, safety guardrails, and compliance with enterprise security protocols.
• Conduct technical exploratory research on emergent foundational models and developer tooling.

Requirements & Experience

• 4+ years of professional software engineering experience with at least 2+ years concentrated on Applied AI and NLP.
• Mastery of Python, FastAPI, and asynchronous backend development.
• Extensive experience working with commercial LLM APIs (OpenAI, Gemini, Anthropic) and embedding models.
• Demonstrated capability in building production-ready RAG architectures and hybrid vector/keyword search.
• Solid grasp of prompt engineering, few-shot prompting, and context-window optimization techniques.
• Familiarity with containerized deployments (Docker, Kubernetes) and cloud GPU instances.

Core Tech Stack

What We Offer

Our Interview Process