AI/ML Engineer – Agentic

About the team:

You will be joining a newly formed and fast-growing team that is dedicated to innovation and excellence. This team leverages the latest technologies and adheres to modern development standards to create state-of-the-art logistics solutions. Designed for global use, our products aim to set new standards in the industry, solving complex challenges with precision and scalability. By joining this forward-thinking team, you will have the opportunity to contribute to a project with a global vision and a strong focus on quality and impact.

About the Role

We are on a mission to accelerate intelligent transformation through cutting-edge artificial intelligence capabilities. We are looking for an experienced and highly motivated AI/ML Engineer to develop the design and implementation of agentic AI systems, LLM-based pipelines, and end-to-end machine learning workflows across both enterprise and customer-facing domains.

In this role, you will architect and deploy multi-agent AI systems that combine large language models, retrieval-augmented generation (RAG), predictive machine learning models, and human-in-the-loop mechanisms. You will play a critical role in shaping scalable, safe, and adaptive AI-driven automation by collaborating closely with software, data, security, and platform teams.

Location: Libadiye Office

Role Overview

As an AI/ML Engineer – Agentic & LLM Pipelines, you will be responsible for building production-grade AI systems that integrate LLMs, classical ML models, and orchestration frameworks into reliable, observable, and scalable solutions. Your work will directly impact intelligent workflows, operational automation, and AI-powered customer experiences.

Key Responsibilities

• Design and implement multi-agent architectures with orchestration logic for complex, multi-step workflows
• Build and deploy agentic AI systems using frameworks such as Microsoft Agent Framework, CrewAI, LangGraph, LangChain, LangFlow, and N8N
• Develop and train ML models including classification, regression, recommendation, and clustering using scikit-learn, XGBoost, LightGBM, and HuggingFace
• Integrate LLM and ML outputs through RAG pipelines, semantic search, vector search, and agent memory architectures
• Perform feature engineering, data preprocessing, and missing data handling to ensure model robustness
• Design and maintain end-to-end MLOps pipelines using MLflow, Kubeflow, Docker, and Kubernetes across Azure, AWS, or GCP
• Fine-tune LLMs and ML models using embedding strategies, hyperparameter optimization, quantization, or distillation techniques
• Implement model evaluation and monitoring using metrics such as accuracy, precision, recall, F1, ROC-AUC, and MSE
• Build and monitor guardrails, reflection loops, output verification layers, and bias or fairness checks
• Implement LLM observability, tracing, and feedback loops using tools such as Langfuse, LangSmith, OpenTelemetry, or custom telemetry pipelines
• Collaborate with cross-functional teams to align AI solutions with business objectives, security constraints, and operational requirements

What Makes You a Great Fit

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related field
• 5+ years of experience delivering production-grade AI and ML systems
• Strong hands-on expertise in agentic AI systems, LLM architectures, and RAG pipelines
• Experience with CrewAI, N8N, LangChain, LangGraph, LangFlow, LangSmith, OpenAI APIs
• Practical experience with Azure AI Foundry, Microsoft Agent Framework, Azure OpenAI Service, Azure ML, and Copilot-aligned agent services
• Strong proficiency in Python (pandas, NumPy, scikit-learn, SciPy, XGBoost) and SQL
• Experience with vector databases such as Pinecone, Weaviate, Chroma, or Qdrant
• Experience with analytical and high-performance databases such as ClickHouse, and familiarity with event-based or time-series data models
• Solid background in statistics, predictive modeling, and ML evaluation methodologies
• Proven experience with MLOps platforms such as MLflow, Kubeflow, SageMaker, Azure ML, and containerized deployments using Docker and Kubernetes
• Familiarity with cloud-native Azure services (Azure Functions, Azure Storage, Azure Event Hub, Azure Kubernetes Service) or equivalent AWS/GCP services
• Experience designing observability, monitoring, and logging for AI systems (Langfuse, Prometheus, Grafana, OpenTelemetry preferred)
• Comfortable using AI-assisted development tools such as Cursor or GitHub Copilot
• Strong communication skills with the ability to explain complex AI concepts to both technical and non-technical stakeholders
• Fluent in English, with a strong analytical and problem-solving mindset

Benefits Of Working With Us

In addition to having the opportunity to grow and be challenged, and to be part of a life, our people enjoy a range of rewarding benefits:

• Flexible working arrangements, generous personal, parental and cultural leave
• Competitive remuneration
• Free and subsidized health and wellbeing services
• Discounts on a wide range of products and services
• Career development opportunities
• A buddy who will guide and accompany you during your onboarding process
• A great number of online courses and technical trainings that will support your development
• Personalized development plan for you
• Using CED & Pass Flight for travelling experience with your family
• Support payment for childcare

Be Yourself

We value the unique backgrounds, experiences and contributions that each person brings to our team and encourage and celebrate diversity.

If you would like to get to know more about Turkish Airlines Technology, please follow us on Instagram and LinkedIn;