AI Engineer (Agent Systems & LLM Platforms)
Description
At Kaizen, we are entering a new era of AI-moving beyond traditional machine learning into intelligent systems powered by Large Language Models, AI agents, and autonomous decision-making pipelines. As an AI Engineer, you will design and build end-to-end AI systems, focusing on AI Agents and multi-agent orchestration, Retrieval-Augmented Generation (RAG), Vector databases & semantic search, and Real-time AI-powered decision systems. You will work at the intersection of software engineering, machine learning, and system design, transforming AI capabilities into production-grade systems used by millions. You will collaborate closely with Platform Engineers and Product teams, contributing to the next generation of AI-driven products at Kaizen.
Responsibilities
- Design and implement AI agents capable of reasoning, planning, and taking actions
- Build multi-agent systems with orchestrators coordinating specialized agents
- Develop workflows for tool usage, memory handling, and decision trees
- Integrate and optimize LLMs (OpenAI, open-source, etc.)
- Design prompt strategies, guardrails, and evaluation frameworks
- Improve reliability, latency, and cost efficiency of LLM-based system
- Build Retrieval-Augmented Generation (RAG) pipelines
- Design chunking, embedding, and retrieval strategies
- Ensure high-quality context injection and grounding of responses
- Work with vector databases
- Design scalable embedding pipelines
- Optimize similarity search and ranking
- Design scalable AI architectures for real-time and batch use cases
- Build APIs and services for AI model interaction
- Handle latency, concurrency, and cost optimization
- Implement evaluation pipelines for AI outputs (quality, hallucinations, drift)
- Monitor system performance and user interactions
- Continuously improve system accuracy and robustness
- Develop reusable frameworks for: Agent orchestration, RAG pipelines, Prompt/version management
- Contribute to internal AI platforms and developer tooling
Requirements
- Strong software engineering experience in Python
- Experience building production-grade systems at scale
- Hands-on experience with: LLM APIs (e.g. OpenAI, Azure OpenAI), Prompt engineering & evaluation, Experience building RAG systems or AI assistants
- Architecture & Systems Thinking and understanding of: Distributed systems, Microservices & APIs, Event-driven architectures
- Search & Retrieval and experience with: Vector databases, Embeddings & semantic search, Information retrieval concepts
- Familiarity with: MLflow, Kubeflow, or similar tools, CI/CD pipelines for AI systems
- Experience with Azure, AWS, or GCP
- Understanding of containerization (Docker, Kubernetes)
- Strong problem-solving skills
- Ability to work in autonomous, cross-functional teams
- Passion for building cutting-edge AI systems
Benefits
- A buddy will support you with your onboarding
- Competitive pay & bonus scheme
- Developmental 360° feedback framework
- Family Support
- Hybrid way of working
- Monthly meal allowance
- Private Health Insurance
- Private health insurance for you & your family
- Unlimited access to Udemy & continuous training
