AI Tooling Engineer

About the role

A partner company is looking for an AI Tooling Engineer based in Turkey to develop and scale an internal agentic platform that combines company knowledge, data and tools in one secure, accessible environment. Working closely with a Principal Engineer, you will build production-ready AI agents and integrations so employees and their AI assistants can find the information they need. The role covers the full lifecycle, from understanding user needs to deployment, monitoring and continuous improvement, and is fully remote.

Key responsibilities

• Help develop and maintain an internal AI platform covering agent development, systems integration, production engineering and continuous optimization.
• Collaborate with the Principal Engineer to design, develop and deploy new platform capabilities, owning each from design through production release.
• Integrate internal systems and SaaS applications by connecting APIs and data sources, defining shared data models and setting access permissions.
• Build AI agents and tools, including MCP servers that let agents interact with internal systems and retrieve context.
• Improve retrieval workflows, tool calling, embeddings, prompts and context management for accurate AI responses.
• Set AI quality standards through evaluation datasets, benchmarks, regression testing, tracing and observability.
• Monitor metrics such as cost per answer and token usage, and optimize models, prompts and workflows.
• Turn proofs of concept into secure, scalable cloud applications with proper infrastructure, deployment and identity and access controls.
• Use AI coding agents in the workflow while keeping code quality through specs, tests, reviews and engineering practices.
• Support other teams in adopting the platform and engage stakeholders to understand their needs.

Required profile

• At least 3 years of experience building and shipping production software, mainly with Python and relational databases.
• Proven experience building and deploying at least one production AI agent with LangGraph used by real users.
• Strong understanding of AI evaluation methods, including test datasets, LLM-as-judge approaches, regression testing and performance monitoring.
• Excellent written and spoken English; familiarity with remote, globally distributed teams is desired.

Required skills

• Hands-on experience with LLM APIs, token management and cost optimization.
• Experience with MCP or similar tool protocols, as server and client.
• Cloud infrastructure on GCP, AWS or both, including containers, managed databases, IAM and CI/CD.
• Version control such as GitHub or Bitbucket; security principles and least-privilege access.
• Desired: Django and PostgreSQL with pgvector, React or Next.js, web scraping, semantic layers, agent memory and multi-agent architectures.

What we offer

• Fully remote work.
• Opportunity to shape AI tooling used across the organization and own end-to-end engineering projects.
• Join a self-motivated, multicultural team with a focus on innovation and autonomy.