AI Software Engineer

Arfitect, founded in 2017 and based at Ege Teknopark, Izmir, is an AI-first custom software and AI consultancy. We build AI-powered enterprise applications for leading companies in energy, manufacturing, aviation and retail, and we develop our own AI SaaS products. Our culture values teamwork, innovation and continuous learning – a place where talent thrives.

We are looking for a software engineer who builds with AI: a developer with a solid backend foundation who turns LLMs, RAG and agent architectures into reliable, production-grade product features. You will join our AI team, working side by side with our current AI engineer and our backend and frontend developers. Your focus is applied AI development on client and product work: our AI R&D track explores new models and techniques, and you turn what proves valuable into systems that run in production. This is an engineering role, not a research or data-science position: we care about what works in production.

• •Design, build and ship LLM-powered features and services – RAG pipelines, tool-using agents, multi-agent workflows – taking ideas from prototype to production as clean, tested, maintainable code.
• •Build the APIs and services (Python/FastAPI, .NET Core) through which our applications consume AI capabilities; agree contracts and integration details with backend and frontend developers.
• •Define what “good” looks like: build evaluation sets and automated regression tests for prompts, retrieval and agent behaviour; analyse failure modes and fix them.
• •Engineer for production qualities: response time, predictable behaviour, traceability and token cost.
• •Apply guardrails: structured outputs, server-side authorization, prompt-injection defences, data-privacy constraints.
• •Build reusable components – MCP servers, agent tools and skills, prompt and retrieval modules – that can be carried from one project to the next.
• •Work closely with our AI R&D track: take validated prototypes to production, and feed real-world findings and failure cases back into it.
• •Evaluate models and tools within your own projects, and stay current with the field.
• •Deploy and operate AI services on Azure with CI/CD, logging and monitoring.
• •Document your work and explain results to the team and clients.

• •2–4 years of professional software development experience (backend-focused), including at least 1 year building LLM-based features that reached real users – beyond simple API calls.
• •Strong Python, plus solid software engineering fundamentals: REST API design, async programming, automated testing, Git, code review, CI/CD.
• •Experience with .NET Core / C#, or willingness to work in it – it is the main stack of our enterprise projects. A strong plus.
• •Hands-on work with LLM APIs (Azure OpenAI, OpenAI, Anthropic): tool/function calling, structured outputs, prompt design, context management.
• •Practical RAG experience: chunking, embeddings, hybrid search, reranking, and a vector store (pgvector, Azure AI Search, Qdrant, ChromaDB or similar).
• •Experience with an agent framework (LangGraph, LangChain, LlamaIndex, Semantic Kernel) or with building your own orchestration.
• •SQL and relational database knowledge (SQL Server / PostgreSQL).
• •Docker and cloud deployment experience (Azure preferred).
• •Daily, effective use of AI coding tools (Claude Code, Cursor or similar).
• •English fluency.

• •High agency: you take ownership of ambiguous problems, find a way through, and ship.
• •Product mindset: you think in terms of user and business outcomes, not just model metrics.
• •Curious and quick to learn in a field that changes every month – and generous in sharing what you learn.
• •A clear communicator with both technical and non-technical people.

• •Local / on-prem LLM deployment (vLLM, Ollama) and fine-tuning of open-source models (LoRA/QLoRA).
• •Speech and voice AI (Whisper, Azure Speech, voice agents).
• •n8n or similar workflow-automation tooling.
• •LLM observability and evaluation tools (Langfuse, LangSmith, Ragas or similar).
• •React/TypeScript, Supabase or Vercel experience – enough to ship a feature end to end.
• •Experience delivering software to large enterprise clients.
• •GitHub profile, portfolio of AI projects, or publications.

Bachelor’s Degree in Computer Science, Software/Computer Engineering, Mathematics or other related field from a four-year College or University.