AI Engineer (Agent & Solution Engineering)

Quick Facts

• Role: AI Engineer (Agent & Solution Engineering)

• Focus: Designing and engineering AI agents and LLM-based solution applications for production

Description

Design, build, test, and develop production-ready AI solutions using an AI Platform, including agent-based architectures and applications built with LLMs, RAG (Retrieval-Augmented Generation), and integrations to business systems. Implement agent orchestration flows, context and memory handling, tool calling, and quality validation/evaluation. Collaborate with business, product teams, architects, and the AI Platform team to deliver scalable and secure solutions.

Responsibilities

• Design and implement AI agent architectures and generative AI applications

• Implement agent patterns, multi-step workflows, and orchestration mechanisms

• Build context engineering strategies, RAG, tool calling, and conversational state/memory

• Define response schemas, validation, and quality-control mechanisms

• Develop solutions using agent templates and platform libraries

• Implement LangGraph flows, prompts, tools, and business logic

• Integrate models via the AI Gateway and organizational knowledge sources

• Implement REST API integrations with business systems

• Manage agent/prompt configuration, knowledge sets, and execution rules

• Create unit, integration, and evaluation tests

• Validate response quality and agent behavior across scenarios (hallucinations, incorrect answers, missing knowledge, functional regressions, human handoff)

• Define quality and acceptance criteria for AI solutions

• Implement monitoring for quality, costs, and performance; analyze logs and execution traces

• Optimize model usage cost and application speed

• Version code, prompts, configuration, and test datasets

• Prepare applications for production deployment using Docker containers

• Participate in code reviews and architectural reviews

• Support production deployments with the AI Platform Engineer

• Create examples, implementation patterns, and onboarding materials for other development teams

Requirements

• 3–5 years of experience building backend applications or AI solutions

• Very good knowledge of Python, Git, API design, and software testing

• Experience building and maintaining production applications

• Practical experience with LLM-based applications

• Knowledge of prompt engineering, context engineering, RAG, agent orchestration, tool calling, structured outputs, and evaluation frameworks

• Ability to design AI agent architecture and multi-agent workflows

• Experience optimizing answer quality and reducing hallucination risk

• Knowledge of Docker and containerization

• Knowledge of SQL and relational databases

• Ability to design and integrate REST APIs

• Experience analyzing logs and debugging application errors

• Understanding of secure software development practices

Benefits

• Interesting challenges and collaboration with experienced IT professionals

• Involvement in deploying and developing a new enterprise AI platform

• Ownership and real impact on the organization’s AI transformation direction

• Latest IT technologies

• Enterprise stability