Senior AI Engineer

We are looking for an experienced Senior AI Engineer to design, develop, and deploy advanced AI-powered solutions in real-world business environments. In this role, you will take ownership of the full development lifecycle of generative AI applications, from model adaptation and information retrieval to agent orchestration, quality assurance, and production deployment.

You will work on technically challenging projects where reliability, scalability, performance, and measurable business impact are essential.

• Agentic AI development: Design and implement autonomous and semi-autonomous AI workflows, including planning, task execution, tool integration, context management, and fault recovery.

• LLM development and optimization: Adapt and deploy open-source language models, apply parameter-efficient fine-tuning techniques, and optimize inference performance, latency, and operational costs.

• Retrieval-augmented generation: Develop and maintain RAG pipelines incorporating embeddings, document retrieval, reranking, and context grounding.

• Reliable AI outputs: Implement structured generation, output validation, safety mechanisms, and post-processing strategies to improve consistency and minimize hallucinations.

• Evaluation and quality assurance: Build automated testing and evaluation frameworks for language models and AI agents, including benchmark suites, regression testing, production monitoring, and version control for prompts and models.

• Production deployment: Develop containerized applications and APIs, establish CI/CD workflows, and implement monitoring, observability, alerting, and reliability practices.

• Technical collaboration: Partner with engineering, product, data, and infrastructure teams to integrate AI capabilities into existing systems and business processes. Contribute to technical decision-making and support the development of other engineers.

• At least 5 years of experience developing and deploying production-grade AI, machine learning, or software systems, including 2+ years in a senior or technical leadership role.

• Strong Python programming skills, including software architecture, automated testing, performance optimization, and maintainable code design.

• Practical experience building and deploying LLM-powered applications and agentic workflows, including tool calling, orchestration, and integration with existing services.

• Experience adapting language models using techniques such as LoRA, QLoRA, PEFT, or comparable approaches.

• Hands-on experience designing and operating retrieval-augmented generation (RAG) solutions.

• Solid understanding of model evaluation, output quality, and AI safety considerations.

• Experience with MLOps practices, containerization, CI/CD pipelines, versioning, and production monitoring.

• Experience developing and maintaining APIs and backend services, including authentication, rate limiting, error handling, and resilience.

• Familiarity with at least one major cloud platform, such as AWS, Google Cloud, or Microsoft Azure.

What Success Looks Like

• Delivering reliable, scalable AI applications that solve practical business problems.

• Improving model quality, inference efficiency, and end-to-end system performance.

• Establishing repeatable evaluation and deployment practices for AI-powered products.

• Building maintainable systems that integrate seamlessly with existing technical environments.

• Contributing to engineering excellence through collaboration, knowledge sharing, and sound technical judgment.

• Ability to translate technical requirements into robust, maintainable, and production-ready solutions.

• Experience optimizing LLM inference through quantization, batching, caching, or GPU-based serving technologies.

• Familiarity with model-serving frameworks such as vLLM, Text Generation Inference, or equivalent solutions.

• Knowledge of AI security practices, including prompt injection mitigation, secure tool execution, sandboxing, and adversarial testing.

• Experience with advanced evaluation methodologies, including model-based judging, rubric-driven assessment, preference evaluation, and A/B testing.

• Experience optimizing vector search systems, embedding pipelines, and retrieval performance.

• Familiarity with event-driven architectures and workflow orchestration platforms.

• Experience building multilingual AI applications and supporting internationalization requirements.

• Közvetítési nyilvántartási szám: PEM/01/002325-1/2017-854