AI Backend Engineer (Agent Systems) - Ruby

Taraki; Islamabad; On-site; PKR 1,500,000 - 2,200,000; Full time

Job summary

A technology company in Islamabad is seeking an AI Backend Engineer to design and implement intelligent systems. You will work on architecting backend services and integrating various tools and APIs. The ideal candidate has experience with AI agent systems, async programming, and cloud deployments. This role offers highly competitive compensation and the opportunity to work with a dynamic team.

Qualifications

• Experience designing AI agent systems with multi-step reasoning.
• Hands-on with async programming and task queues.
• Practical mindset focused on reusing existing APIs.

Responsibilities

• Design and implement multi-step reasoning architectures.
• Integrate external tools and APIs into agent workflows.
• Monitor and optimize system reliability and performance.

Skills

AI agent systems design

Async programming

Cloud deployment

CI/CD

Docker

Tools

FastAPI

GitHub

Redis

Celery

Job description

About the job AI Backend Engineer (Agent Systems) - Ruby

About Ruby

Ruby is building vertical‑specific AI agents for go‑to‑market (GTM) teams, backed by leading investors such as Inovia and NJP and used by customers at F1000 companies. Our team combines deep LLM expertise with domain knowledge to build a product that is practical, scalable, and reliable. The founding team has worked at companies like Snowflake and Salesforce in senior roles.

We're growing our engineering team and looking for someone who thrives at the intersection of AI reasoning, backend systems, and automation.

About the Role

As an AI Backend Engineer, youll design and implement systems that power intelligent agents and AI capable of reasoning, using tools, and orchestrating multi‑step workflows.

Youll work closely with our applied AI and product teams to ship reliable, production‑ready agent services built on top of cutting‑edge models from OpenAI, Anthropic, and Gemini.

What Youll Do

• Design and implement multi‑step reasoning architectures and tool‑calling agents using OpenAI, Anthropic, and Gemini APIs.
• Build modular, scalable backend services with FastAPI (or similar frameworks), managing state, retries, and parallel execution.
• Integrate external tools and APIs such as GitHub, cloud providers, and databases into agent workflows using structured outputs.
• Develop workflow orchestration logic with async execution, background tasks, and queues (Redis, Celery, SQS).
• Manage CI/CD pipelines, containerized deployments (Docker), and Infrastructure as Code setups for production environments.
• Monitor and optimize system reliability, performance, and observability for live agent systems.

What Were Looking For

• Experience designing or contributing to AI agent systems with multi‑step reasoning or tool use.
• Experience with async programming, task queues, and state management.
• Hands‑on with cloud deployment, CI/CD, Docker, and Infrastructure as Code.
• A practical mindset focused on reusing existing APIs and libraries to ship fast, reliable systems instead of reinventing the wheel.

Bonus Points

• Familiarity with LangChain, LlamaIndex, or CrewAI‑style orchestration frameworks.
• Experience with vector databases, retrieval‑augmented generation (RAG), or LLM observability.
• Previous work on AI developer tools or production LLM applications.

Why Join Us

• Learn from proven founders: Youll be part of a small, high‑velocity team building the next generation of applied AI systems with founders who have seen it all from idea to IPO.
• Focus on craft: We value curiosity, clarity, and craft and were looking for engineers who care about solving real problems with elegant, reliable code.
• Make an impact: Youll be part of a small team and have an outsized impact.
• Be valued: We offer highly market‑competitive compensation.