Senior Agentic AI Engineer

Rayda; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

Rayda is seeking a Senior Agentic AI Engineer to lead design, development, and deployment of autonomous AI systems that drive intelligent decision-making, workflow automation, and next-generation user experiences. This role requires deep expertise in LLMs, AI agents, multi-agent architectures, orchestration frameworks, and production-grade AI systems.

You will define Rayda's AI strategy and build intelligent agents that can reason, plan, act, and collaborate to solve complex business challenges.

Qualifications

• 7+ years of software engineering experience, including scalable distributed systems.
• 3+ years deploying AI/ML solutions in production.
• Strong Python and modern AI frameworks expertise.
• Experience building AI agents and orchestration systems.
• Expertise with LLMs and prompt engineering.

Responsibilities

• Design, build, and deploy autonomous AI agents and multi-agent systems.
• Architect agentic workflows using planning, memory, tool use, and autonomous execution.
• Develop RAG systems, knowledge pipelines, and vector DB integrations.
• Create scalable orchestration frameworks with LangGraph, CrewAI, AutoGen, OpenAI SDK.
• Collaborate with product and engineering teams to drive AI-enabled automation.

Skills

Python

Distributed systems

AI/ML production

Agent orchestration

LLMs

Prompt engineering

CI/CD / MLOps

API integration

Education

Bachelor's degree in CS/AI/SE

Master's degree preferred

Tools

LangGraph

CrewAI

AutoGen

OpenAI Agents SDK

Docker

MLOps tooling

Job description

Location: United States

This is a remote position.

Job Title:Senior Agentic AI Engineer
Rayda is looking for an exceptional Senior Agentic AI Engineer to lead the design, development, and deployment of autonomous AI systems that drive intelligent decision-making, workflow automation, and next-generation user experiences.

This role is ideal for an engineer with deep expertise in Large Language Models (LLMs), AI agents, multi-agent architectures, orchestration frameworks, and production-grade AI systems. You will play a critical role in defining Rayda's AI strategy and building intelligent agents that can reason, plan, act, and collaborate to solve complex business challenges.

Key Responsibilities

• Design, develop, and deploy autonomous AI agents and multi-agent systems for real-world business applications.

• Architect agentic workflows that leverage planning, reasoning, memory, tool usage, and autonomous execution.

• Build and optimize Retrieval-Augmented Generation (RAG) systems, knowledge retrieval pipelines, and vector database integrations.

• Develop scalable agent orchestration frameworks using tools such as LangGraph, CrewAI, AutoGen, OpenAI Agents SDK.

• Integrate AI agents with internal systems, APIs, databases, enterprise platforms, and third-party tools.

• Implement agent evaluation, monitoring, observability, and guardrail mechanisms to ensure reliability and safety.

• Collaborate with product, engineering, and business teams to identify opportunities for intelligent automation and AI-driven innovation.

• Drive technical leadership, architectural decisions, and AI best practices across the organization.

What You'll Build

• Autonomous AI agents capable of planning, reasoning, and taking actions across enterprise systems.

• Multi-agent ecosystems that collaborate to solve complex operational and customer challenges.

• Intelligent workflow automation that improves productivity, efficiency, and business outcomes.

• Production-ready agentic platforms that scale securely and reliably.

Requirements

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field.

• 7+ years of software engineering experience, including experience building scalable distributed systems.

• 3+ years of hands-on experience developing and deploying AI/ML solutions in production.

• Strong proficiency in Python and modern AI development frameworks.

• Demonstrated experience building AI agents, autonomous workflows, and agent orchestration systems.

• Expertise in Large Language Models (OpenAI, Anthropic, Gemini, Llama, Mistral, or equivalent).

• Strong understanding of prompt engineering, tool calling, function execution, memory systems, and agent planning strategies.

• Experience with vector databases, embeddings, semantic search, and Retrieval-Augmented Generation (RAG).

• Strong knowledge of APIs, microservices, CI/CD pipelines, Docker, and MLOps practices.

Preferred Qualifications

• Experience with LangGraph, CrewAI, AutoGen.

• Experience designing multi-agent collaboration systems and autonomous decision-making workflows.

• Knowledge of AI governance, security, compliance, and responsible AI practices.

• Experience with knowledge graphs, reinforcement learning, or advanced reasoning architectures.

• Startup or high-growth technology company experience.