AI Engineer

AI Delivery Engineer (Agent Tooling & Code Generation) 🤖⚡

ZentixSoft is looking for an AI Delivery Engineer! 🚀
 

Format: Full-Time Outstaffing, long-term remote project. You will build and ship production-grade AI agent tooling and code-generation solutions, embedding AI agents directly into the delivery lifecycle.

💡 Why ZentixSoft? 
💸 Salary Review: A structured system of compensation reviews aligned with your engineering growth. 
⚖️ Work-Life Balance: Sustainable workflows with no senseless overtime, helping you keep your resource fully charged. 
🦾 Trust and Transparency: Zero micromanagement and no invasive time-trackers—we fully trust your professional autonomy. 
🎁 Gifts & Culture: Corporate gifts for holidays, birthdays, and a true team atmosphere where your voice always matters.
 

🧩 Responsibilities:

• AI Tooling & Automation: Design, build, and maintain AI agent tooling that automates engineering and business workflows.
• Code Generation Pipelines: Develop and refine developer copilots and code-generation workflows.
• Agent Integration & RAG: Integrate LLM APIs, agent-orchestration frameworks, RAG pipelines, and vector databases into production systems.
• Production Reliability: Monitor, evaluate, and enhance agent performance, safety guardrails, and reliability from prototype to production rollout.
• Documentation & Adoption: Document tooling, establish prompt engineering standards, and support internal teams in adopting AI agents.
   

🎓 Requirements:

• Engineering Background: 4+ years of commercial software engineering experience, with a recent focus on applied AI/LLM systems.
• Agent Frameworks: Hands-on experience building LLM-based agents or agent-orchestration frameworks (LangChain, LangGraph, AutoGen, or custom pipelines).
• Code-Gen & Copilots: Proven experience with code-generation tooling and AI-assisted development workflows.
• Core Tech Stack: Strong Python skills (TypeScript/JavaScript is a plus) for agent tooling and integration.
• LLM & Vector Ecosystem: Experience working with LLM APIs (OpenAI, Anthropic, etc.), RAG architecture, vector stores, prompt engineering, and guardrails.
• Production Shipping: Demonstrated ability to take AI concepts and prototypes to production-grade deployment.
   

➕ Nice to Have:

• Experience deploying agentic frameworks in enterprise settings.
• Familiarity with MLOps / LLMOps practices.
• Contributions to open-source AI tooling.
   

📍 Project Details:

⏳ Duration: Long-term (Full-time).

📍 Location: Fully Remote.