Senior LLM Engineer

Job Title: Senior LLM Engineer

Location: İzmir 

About Us

Amatis is a technology company that develops AI-powered products and delivers custom technology solutions to organizations. While our current strategic focus is AI in healthcare, we are committed to accelerating digital transformation across sectors—from defense to infrastructure. For over 20 years, we’ve been building systems that matter—scalable, sustainable, and bold.

We don’t just build software;

 We engineer foundations for the future.

Role Overview

We are seeking an experienced Senior LLM Engineer to lead the development of our conversational AI system. You will be responsible for designing and implementing the core AI components including the LLM backend, retrieval-augmented generation (RAG) system, and agent-based architecture that will power our voice-interactive call center solution.

Key Responsibilities

• Design and implement the LLM-based conversational system using open-source models (Mistral, Llama, Gemma ,etc.)
• Develop a high-performance RAG system to retrieve information from company documentation and knowledge bases
• Build an agent-based framework that can interface with multiple backend systems (CRM, billing, tariff systems, etc.)

·      Multi-Agent Orchestration: Proven experience with agent orchestration frameworks including LangChain, n8n, AutoGen, OpenAI Assistants API, and similar multi-agent coordination platforms 

·      Tool-Use/Function Calling: Deep expertise in implementing function calling mechanisms that enable LLMs to interact with external APIs and tools effectively 

·      Agent State Management: Experience managing complex agent states across multi-step processes and maintaining consistency throughout extended interactions 

·      Planning & Reasoning: Proficiency in implementing ReAct (Reasoning + Acting) patterns, Chain-of-Thought prompting techniques, and optimizing agent decision-making processes 

·      Error Handling & Recovery: Demonstrated ability to develop self-correcting agent systems with robust error handling and automatic recovery capabilities 

·      Agent Memory Systems: Experience designing and implementing long-term memory and episodic memory systems for conversational agents 

·       Parallel Agent Execution: Proven track record developing systems where multiple agents can operate concurrently and coordinate effectively 

• Agent Performance Optimization: Expertise in optimizing agent interactions for minimal latency and cost efficiency in production environments
• Fine-tune open-source models for language processing
• Optimize models for deployment in production environments (quantization, inference optimization)
• Implement speech-to-text and text-to-speech components with natural-sounding voice capabilities
• Design dialogue management systems that maintain context throughout customer interactions
• Create confidence scoring mechanisms for determining when to escalate to human operators
• Collaborate with backend developers to ensure seamless system integration
• Continuously improve system performance based on real-world usage data

Required Qualifications

• 3+ years of experience in NLP/ML engineering, with at least 2 years focusing on LLMs
• Strong experience deploying and optimizing open-source LLMs 
• Proven experience with RAG system implementation and vector databases
• Experience with model quantization and inference optimization techniques (GGUF, vLLM, etc.)
• Strong programming skills in Python and ML frameworks (PyTorch, Hugging Face Transformers, etc.)
• Experience with speech-to-text and text-to-speech technologies
• Knowledge of agent-based AI architectures
• Experience with model fine-tuning and domain adaptation
• Solid understanding of DevOps concepts for AI applications (containerization, orchestration)
• Good Command English communication skills 

Preferred Qualifications

• Experience with real-time, low-latency AI systems
• Familiarity with .NET Core environments
• Experience with A/B testing and AI system evaluation methodologies
• History of working with voice-based conversational AI

What We Offer

• Strategic role in high-impact, AI-powered projects
• Complex systems to solve and the freedom to design boldly
• A global team of technologists, product thinkers, and innovators
• Multidisciplinary collaboration in domains that matter—from health to infrastructure
• Transparent, open culture that values ownership, communication, and craft
• Continuous learning, mentoring, and development opportunities
• A rare chance to shape real-world products with real-world impact

How to Apply

 Send your CV and a brief motivation note to [email protected]

 Use the subject line: “Senior LLM Engineer”

 If this sounds like your kind of mission—

 You know what to do. We’re building something big. And we need you.