Top 3 Reasons To Join Us Budget for individual learning & development 14+ leave days/year; premium health insurance Dynamic and open working environment The Job

AI Engineering & Orchestration:

Agentic Systems: Design and deploy autonomous AI Agents, building complex workflows including planning, multi-step reasoning, and tool-use/function calling.
Data & Retrieval: Build and optimize RAG (Retrieval-Augmented Generation) systems using vector databases and embeddings to provide accurate context for LLMs.
AIOps: Establish evaluation pipelines to measure AI quality, minimize hallucinations, and control bias.
Resource Optimization: Monitor and optimize latency, token throughput, and operational costs for AI systems.
AI Integration: Package AI features into stable APIs for seamless integration into the existing Microservices ecosystem.

Backend Engineering:

Core Systems: Design, develop, and manage high-performance backend services, ensuring stability and scalability in production.
Feature Development: Maintain existing systems and proactively develop new functionalities based on business requirements.
International Collaboration: Work closely with the Korean tech team and stakeholders to align on architectural solutions and application deployment.
Code Quality: Apply standard coding practices, ensuring high unit test coverage and optimized debugging processes.
Technology Research: Proactively research new technologies, specifically AI infrastructure solutions, to apply to company projects.

Your Skills and Experience

Mandatory Skills:

Experience: 4–6 years of professional experience, including 1–2 years in backend software development and 3–4 years in AI Engineering. Strong proficiency in Python or Java is required. Candidates with hands-on experience in both languages are preferred, using Python for AI/Data applications and Java for core backend services.
Architecture: Deep understanding of Microservices, RESTful APIs, and gRPC.
Data: Experience with SQL (PostgreSQL, MySQL) or NoSQL (MongoDB, Cassandra).
Fundamentals: Mastery of data structures, algorithms, OOP, and common design patterns.

AI Specialization:

LLM Production: Proven experience implementing features using OpenAI, Claude, or open-source models (Llama, Mistral) in production.
Frameworks: Proficiency in AI orchestration libraries: LangChain, LangGraph, CrewAI, or AutoGen.
Vector Infrastructure: Experience with Vector Databases such as Milvus, Pinecone, Qdrant, or pgvector.
Agentic Skills: Solid understanding of Function Calling, Memory management (Long-term/Short-term), and advanced Prompt Engineering (Chain-of-Thought, ReAct).
AI Quality: Knowledge of evaluation frameworks (e.g., Ragas, Arize Phoenix, or LangSmith).

Nice-to-have:

Experience with high-traffic systems and asynchronous processing.
Proficiency in Docker, Kubernetes, and Cloud platforms (AWS/GCP/Azure).
Experience with Redis (Caching) and Message Brokers (Kafka or RabbitMQ).
Understanding of CI/CD for AI (MLOps).

Why You'll Love Working Here

Health and Wellness

Premium health insurance
Safe, ethical, secure, and healthy workplace

Financial Well-Being

Competitive compensation package
Annual bonus program

Personal Development

Budget for individual learning & development

Work-life balance

14 days of paid annual leave, increasing by 1 day each year
Flexible working timeframe

Workplace experiences

Modern working equipment
Well-stocked pantry to relax and recharge.
Engagement activities (monthly team bonding, yearly company trip…)
Sponsored sports clubs
Business trip opportunities to the Korean Headquarters

Benefits