To apply for this job, you need to complete both steps below:

STEP 1:

Please click the link to submit your application directly to the company: 

Careers

Your application will only be received by Recruiter if submitted via above link. 

STEP 2:

Kindly scroll to the bottom of this page and complete the short VinUni Tracking Form.

Filling out this form alone does not count as applying. Kindly remind this form is not part of the company’s application process. It only helps Careers, Alumni, Industry and Development (CAID) Department discover more opportunities and follow up in case of system issues.

esponsibilities

As an Experienced AI Engineer (AI Agent), you will take ownership of building reliable AI agents for assigned use cases, with a focus on basic evaluation, monitoring, and production quality.

• Develop AI Agents for Product Use Cases
• Develop AI agents for use cases such as conversational Q&A, data retrieval (text-to-SQL / Data Platform querying), compliance review, data analysis, and insight generation — as well as new use cases emerging along the product roadmap.
• Build and optimize RAG pipelines, including chunking, embedding, vector search, reranking, and citation-based responses to ground agents in internal data and documentation and reduce hallucinations.
• Apply prompt engineering, function/tool calling, and structured output; integrate LLMs with APIs, databases, and internal tools, with MCP (Model Context Protocol) as a preferred standard.
• Test and validate AI agent accuracy, continuously optimize agent performance, and ensure safe operation in production environments.
• Production Deployment & Quality Assurance
  
  

Implement basic evaluation (eval), monitoring, and tracing for AI agents; apply existing guardrails such as out-of-scope query handling and authorization enforcement, while optimizing token usage and latency according to product requirements.

Translate business requirements into AI agent workflows with clear error handling and fallback mechanisms; collaborate with Analytics, Backend/Data, and Product teams to bring AI capabilities into production.

——————

As a Senior AI Engineer (AI Agent), you will design AI agent systems that maximize the value of a unified and interconnected data platform. You will define technical standards for multi-agent systems, semantic layers, and release-gating evaluation, ensuring that the platform is reliable, secure, and scalable for sensitive cybersecurity data.

As use cases continuously expand with user needs and the product roadmap, you will design a general-purpose and reusable agent platform — including shared tools/MCP, semantic layers, and evaluation frameworks — that enables rapid development of new use cases while maintaining quality. You will also provide technical leadership and mentorship to the AI engineering team.

• AI Agent Architecture & System Development
• Design end-to-end AI agent architectures for use cases such as conversational Q&A, Data Platform querying (text-to-SQL / semantic layer), compliance review, data analysis, and new use cases driven by the product roadmap.
• Design multi-agent workflows with agent handoffs, fallback mechanisms, and human-in-the-loop controls for irreversible or high-impact actions.
• Build a semantic layer with consistent definitions of metrics, entities, and data lineage to improve agent reasoning and query generation across the unified data platform; standardize reusable tools/MCP services across the platform.
• Build and evolve production-grade RAG systems, including hybrid search, reranking, retrieval quality optimization, and citation-based responses; establish data-driven mechanisms for continuously measuring and improving retrieval quality.
• Quality, Reliability & Security
• Build an evaluation framework that gates deployment, including golden datasets, model-graded evaluation, and regression suites integrated into CI pipelines; establish end-to-end observability and tracing.
• Optimize LLM usage, latency, and cost; design monitoring and usage-management mechanisms across AI agents.
• Design AI agents with protection against prompt injection, data leakage, unauthorized access, and other AI-specific security risks.
• Make architectural decisions around scalability and maintainability; evaluate and select technologies aligned with the system architecture and product requirements.
• Technical Leadership & Collaboration
• Provide technical leadership through mentoring Middle/Junior engineers, conducting code reviews, and collaborating with Product, Data, and DevOps teams to improve the team’s engineering capabilities and delivery efficiency.
  
  

Qualifications

Experienced AI Engineer (AI Agent)

• 3+ years of experience in software development and/or AI/ML, including hands-on experience building products powered by LLMs or AI agents.
• Strong proficiency in Python and solid software engineering fundamentals, including Git, REST APIs, modular design, and unit testing.
• Hands-on experience integrating LLM APIs, including prompt engineering, function/tool calling, and structured output.
• Practical experience building RAG systems, including embeddings, vector databases such as Qdrant, Milvus, or pgvector, retrieval, and citation.
• At least one hands-on Agentic AI project using frameworks such as LangGraph, LangChain, CrewAI, or AutoGen.
• Experience working with tabular and text data.
• Bachelor’s degree in Computer Science, Information Technology, Cybersecurity, or a related field.
  
  

Bonus Points

• Experience with MCP (Model Context Protocol) and/or text-to-SQL / semantic layers.
• Basic LLMOps experience, including evaluation frameworks such as RAGAS, DeepEval, or promptfoo, and observability tools such as Langfuse or LangSmith.
• Knowledge of system architecture, including SQL/NoSQL databases, containers, message queues, and big data technologies such as Spark and notebooks.
• Strong systems thinking and a product-oriented mindset.