Job Title:AI Developer
Level: Mid & Senior
Location:Urla, Izmir
Type: On-site
About Efsora
We are a fast-growing software and AI development company that partners with innovative enterprises and scaleups to deliver large, cutting-edge R&D projects.
Our teams work as extensions of our clients’ internal R&D, combining advanced technology expertise, AI-centric engineering, and agile development to build impactful solutions.
We focus on augmenting our clients’ R&D capabilities, accelerating innovation, and managing technical risks from early-stage prototyping to full-scale deployment.
As part of our team, you’ll work on exciting, high-stakes projects that shape the future of industries, collaborate with top-tier talent, and grow your skills at the frontier of AI and software development.
The Opportunity
We are seeking a talented and experiencedAI Developerwith a strong focus onLLMsandagentic architecturesto join our team.
You will play a pivotal role in designing, developing, and deploying cutting-edge, goal-oriented AI solutions that will enable automated problem-solving, create adaptive user experiences, and drive autonomous operational efficiency — to name just a few key use cases.
What You'll Do
- Lead the design and implementation of agentic architectures and autonomous AI systems leveraging Large Language Models (LLMs) as core reasoning and interaction components.
- Develop strategies for LLM-powered planning, memory management, tool integration, and multi-step reasoning.
- Architect and build robust orchestration layers that enable LLMs to interact with external APIs, databases, and other systems to achieve complex goals.
- Design, develop, and maintain backend services and APIs that power our AI applications, ensuring scalability, performance, and security.
- Design and implement specialized techniques for prompt engineering, few-shot learning, in-context learning, and fine-tuning to optimize LLM performance within agentic workflows.
- Develop robust evaluation metrics and methodologies for agent performance, focusing on task completion, efficiency, robustness, and failure modes.
- Collaborate closely with product managers and other AI & software developers to understand complex business requirements and translate them into practical, autonomous AI solutions.
- Deploy and maintain sophisticated LLM-based agentic applications in production environments, ensuring their reliability, efficiency, and continuous improvement, including monitoring, cost optimization, and safety mechanisms.
- Stay up-to-date with the latest advancements in LLM research, NLP, AI agents, reinforcement learning, and MLOps, bringing new ideas and approaches to the team.
- Participate in code reviews, technical discussions, and contribute to the overall architecture and design of our intelligent agent systems.
What We're Looking For:
Experience:
- 3+ years of professional experience in developing and deploying AI/ML models, with a significant portion focused on NLP/NLG and demonstrable experience with agentic systems.
LLM Proficiency:
- Deep practical experience with Large Language Models, including:
- Advanced use and fine-tuning of models from libraries like Hugging Face Transformers
- Extensive experience with LLM APIs (e.g., OpenAI GPT, Anthropic Claude, Google Gemini)
- Expertise in prompt engineering, few-shot learning, and in-context learning
Agentic System Design:
- Experience in designing and implementing agentic architectures, including concepts like:
- Planning and reasoning loops
- Memory management (short-term and long-term)
- Tool/function calling and integration
- Multi-agent systems
Programming:
- Strong proficiency in Python and relevant AI/ML/NLP libraries (e.g., PyTorch, TensorFlow, Keras, spaCy, NLTK)
Problem-Solving:
- Exceptional analytical and problem-solving skills, with the ability to architect and debug complex, interdependent AI systems
Collaboration:
- Strong communication and collaboration skills, with the ability to lead technical discussions and work effectively in a team environment
Bonus Points If You Have
- Direct experience with agent orchestration frameworks (e.g., LangGraph, LlamaIndex, AutoGen)
- Understanding of Reinforcement Learning from Human Feedback (RLHF) and its applications in agentic training
- Experience with control flow and state management in complex AI systems
- Experience with Model Context Protocol (MCP)
- Experience with Streamlit, Gradio, or Dash for rapid prototyping and deployment of AI/ML demos and applications
- MLOps experience, especially in deploying and monitoring complex, stateful agentic systems in production on cloud platforms (AWS, Azure, GCP), including containerization (Docker) and orchestration (Kubernetes)
- Familiarity with CI/CD pipelines for full-stack deployments
- Contributions to open-source projects or a strong GitHub profile
- Experience in a startup or fast-paced environment