AI Engineer at Inetum

Bucharest, , Romania -

Full Time

Start Date

Immediate

Expiry Date

12 Jan, 26

Salary

0.0

Posted On

14 Oct, 25

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

AI Solutions Deployment, LLMs, Prompt Engineering, Multi-Agent Systems, Python, NLP, Data Privacy, Ethical AI, A/B Experimentation, Agent Communication, Task Decomposition, Model Deployment, API Integration, Iterative Testing, Performance Analysis, Prompt Refinement

Industry

IT Services and IT Consulting

Description

Company Description About Inetum Inetum is a European leader in digital services. Inetum’s team of 27,000 consultants and specialists strive every day to make a digital impact for businesses, public sector entities and society. Inetum’s solutions aim at contributing to its clients’ performance and innovation as well as the common good. Present in 19 countries with a dense network of sites, Inetum partners with major software publishers to meet the challenges of digital transformation with proximity and flexibility. Driven by its ambition for growth and scale, Inetum generated sales of 2.4 billion euros in 2024. For further information, please visit www.inetum.com Job Description Develop, refine, and optimize prompts for LLMs (GPT-4, Gemini, Claude, Llama, Mistral) to support a variety of tasks such as text generation, summarization, Q&A, and code generation Design and implement prompt strategies for multi-turn conversations, prompt chaining, and role-based instructions Build and coordinate groups of AI agents (multi-agent systems) for collaborative or competitive tasks using frameworks such as Lang Chain, Crew AI, or Auto Gen Upgrade existing prompts while releases and solutions set evolve Evaluate and improve the effectiveness of prompts and agent workflows through iterative testing, A/B experimentation, and performance analysis Collaborate with cross-functional teams (developers, data scientists, product managers) to integrate prompt engineering and agentic workflows into enterprise solutions Ensure compliance with data privacy, security, and regulatory standards (GDPR, NIS2) in all prompt and agent designs Document prompt strategies, agent architectures, and best practices for internal knowledge sharing and training Ensure provided solutions are ready for production, documented and monitored ensuring consistent delivery and quality Qualifications Minimum 3 to 5 years of experience in AI solutions deployment in enterprise environments. Understanding of how LLMs (GPT-4, Gemini, Claude, Llama, Mistral AI) work, their capabilities, and limitations. Familiarity with model architecture, tokenization, context windows, and prompt formatting Crafting effective prompts for various tasks (text generation, summarization, Q&A, code generation, images and sound manipulations) Techniques for prompt chaining, few-shot and zero-shot learning, and multi-turn conversations Knowledge of prompt templates, system instructions, and role-based prompting Understanding the concept of AI agents: autonomous entities that perceive, reason, and act to achieve goals Familiarity with multi-agent systems, agent orchestration, and agentic workflows (e.g., using frameworks like Lang Chain, Crew AI, Auto Gen) Ability to design, prompt, and coordinate groups of AI agents for collaborative or competitive tasks Knowledge of agent communication, delegation, and task decomposition Knowledge of data acquisition protocols like MCP Understanding of NLP concepts such as intent detection, entity recognition, sentiment analysis, and text classification Awareness of biases, hallucinations, and ethical considerations in AI-generated content Proficiency in Python (most common for AI workflows), and familiarity with libraries such as Lang Chain, Hugging Face Transformers, and OpenAI API Ability to automate prompt testing, evaluation, and deployment Methods for evaluating prompt effectiveness (accuracy, relevance, coherence) Techniques for prompt refinement, iterative testing, and A/B experimentation Experience with platforms like OpenAI, Azure OpenAI, Google Vertex AI, AWS Bedrock, and Hugging Face Familiarity with model deployment, API integration, and workflow orchestration. Understanding of data protection regulations (GDPR, NIS2) and responsible AI practices Awareness of risks related to sensitive data in prompts and outputs Additional Information Benefits: Full access to foreign language learning platform Personalized access to tech learning platforms Tailored workshops and trainings to sustain your growth Medical Insurance Meal tickets Monthly budget to allocate on flexible benefit platform Access to 7 Card services Wellbeing activities and gatherings

Responsibilities

The AI Engineer will develop and optimize prompts for large language models to support various tasks, including text generation and Q&A. They will also design multi-agent systems and ensure compliance with data privacy and security standards.