AI Engineer

Artyreal is a creative software studio specializing in design, branding, software products, and video production for clients worldwide. Our team combines storytelling, design, and technology to create engaging work that resonates with audiences. We prioritize creativity, ownership, clear communication, attention to detail, and a strong eagerness to learn. We are currently seeking an AI Engineer to develop AI products and automations for our ventures and clients across Pakistan. This role involves designing and building LLM-powered applications, AI agents, retrieval-augmented generation (RAG) systems, and workflow automations, taking projects from prototype to production. It is a hands-on position suited for an early-career engineer with solid fundamentals, some shipped projects, and a passion for AI’s current capabilities.

Key Responsibilities
- Develop LLM-powered applications and AI agents using models from OpenAI, Anthropic, Google, and open-source providers.
- Design and implement RAG pipelines including document ingestion, chunking, embeddings, vector search, and retrieval tuning.
- Build agentic workflows featuring tool calling, structured outputs, memory, and multi-step reasoning.
- Create workflow automations connecting AI with business tools such as CRMs, WhatsApp, email, Google Workspace, and Slack using n8n, APIs, and webhooks.
- Build web applications, internal tools, and MVPs end-to-end using Claude tools, including Claude Code for AI-assisted development and the Claude API for AI features.
- Collaborate with product and frontend teams to integrate AI features into web and mobile products.
- Write, iterate, and version prompts and system instructions like code.
- Set up evaluation processes to measure accuracy, hallucinations, and regressions before deployment.
- Monitor production systems for cost-efficiency, latency, and reliability, optimizing where necessary.
- Ensure responsible data handling by securing API keys, protecting client data, and preventing prompt injection.
- Scope technical solutions with the team and clearly explain trade-offs to non-technical clients.
- Stay updated on new AI models, tools, and techniques, testing and adopting what adds value.

Required Qualifications
- 0 to 2 years of software development experience, with at least one AI or LLM project shipped (professional, freelance, hackathon, or personal).
- Strong proficiency in Python, writing clean, tested, production-ready code.
- Hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini, or similar), including tool calling and structured outputs.
- Understanding of RAG, embeddings, and vector databases such as pgvector, Pinecone, Qdrant, or Chroma.
- Experience building REST APIs using FastAPI, Flask, or Node.js.
- Comfortable shipping full applications using AI coding tools, especially Claude Code, leveraging AI to accelerate development without compromising quality.
- Working knowledge of SQL and at least one database system (PostgreSQL, MongoDB, or similar).
- Proficient with Git, debugging, and collaborating in shared codebases.
- Clear communication skills with the ability to explain technical decisions simply.
- Degree in Computer Science, Software Engineering, AI, Data Science, or related field, or equivalent hands-on experience.

Preferred Qualifications
- Experience with agent frameworks such as LangGraph, LangChain, LlamaIndex, OpenAI Agents SDK, or Claude Agent SDK.
- Familiarity with Model Context Protocol (MCP) servers and tool integrations.
- Automation experience using n8n, Make, or Zapier.
- TypeScript and Next.js experience for delivering full-stack AI features.
- Knowledge of Docker and cloud deployment platforms like AWS, GCP, Azure, or Vercel.
- Experience with evaluation and observability tools such as Langfuse or LangSmith.
- Running or fine-tuning open-source models (Llama, Qwen, Mistral) using Hugging Face, Ollama, or vLLM.
- Experience in voice AI, speech-to-text, or OCR technologies.
- Handling Urdu or Roman Urdu text and speech in AI systems.
- Integrations with WhatsApp Business API or Meta Graph API.
- Active GitHub presence, open-source contributions, or hackathon achievements.

Benefits
- Competitive monthly salary based on skills, plus performance bonuses.
- Opportunity to ship real AI products used by businesses across Pakistan, not just demos.
- Direct collaboration with founders on product and architecture decisions.
- Exposure to diverse problem spaces across internal products and client projects.
- Clear growth path toward senior AI engineer or AI lead roles.
- Fast-paced studio environment offering real ownership and impact.

This is a full-time, permanent position based onsite at our Islamabad office with an expected commitment of 40 hours per week. Applicants are invited to apply through the application form available on our website.