AI Engineer: Build Production LLMs & Secure AI Systems

Paribu; Fatih; On-site; TRY 360,000 - 600,000; Full time

Benefits offered by this job

Meal allowance

Private health insurance

Commuting support

S.O.S. leave (10 days)

Birthday leave

Language learning support

Personal development support

Well-being & health platform

Relocation allowance

Top-tier work equipment

Cultural events

Job summary

Paribu is seeking an AI Engineer to design, build, and operate production-grade LLM applications, including RAG pipelines and agent/tool integrations. You will develop scalable back-end services and APIs powering AI products and internal knowledge systems, while establishing observability for quality, latency, and cost.

You will collaborate with engineering and business stakeholders, ensuring secure, governance-focused AI systems and efficient deployment in a cloud/Kubernetes environment.

Qualifications

• Hands-on experience building production-grade LLM applications, including RAG, embeddings, hybrid search, reranking, prompt engineering, and agent/tool-use architectures.
• Strong backend engineering skills with Python and/or TypeScript/Go, API design, asynchronous systems, databases, vector stores, and message queues.
• Experience evaluating and monitoring LLM systems with eval sets, metrics, tracing, latency and cost optimization.

Responsibilities

• Designing, building, and operating production-grade LLM applications and RAG pipelines.
• Building scalable backend services and APIs powering AI products and knowledge systems.
• Developing observability practices to measure model quality, latency, and cost.

Skills

LLM applications

Python

TypeScript/Go

APIs

Kubernetes

CI/CD

GitHub

Security & governance

Data privacy

Cross-functional collaboration

Tools

GitHub

Slack

CI/CD pipelines

MCP-based tools

Job description

Paribu is seeking an AI Engineer to design, build, and operate production-grade LLM applications, including RAG pipelines and agent/tool integrations. You will develop scalable back-end services and APIs powering AI products and internal knowledge systems, while establishing observability for quality, latency, and cost.

You will collaborate with engineering and business stakeholders, ensuring secure, governance-focused AI systems and efficient deployment in a cloud/Kubernetes environment.