This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
We’re hiring a Generative AI Engineer for our AI-powered modernization platform (iBEAM). Role involves building RAG pipelines, AI agents, LLM integrations & scalable Python services for enterprise transformation use cases.
Job Responsibility:
Design, develop, and deploy Generative AI–powered software solutions
Build robust, scalable Python services integrating Large Language Models (LLMs)
Craft and optimize advanced prompts to enforce accuracy, tone, formatting, and guardrails
Fine-tune and adapt LLMs for domain-specific and business-critical use cases
Architect and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines
Develop autonomous and semi-autonomous AI agents
Integrate LLMs with external APIs, databases, and computation engines
Evaluate and monitor model behavior to detect hallucinations, drift, and quality regressions
Write production-grade, modular Python code and participate in code reviews
Stay current with emerging research, tools, and best practices in Generative AI
Requirements:
Hands-on experience working with foundation models such as GPT-4, Claude, Llama 3, or Mistral to build real-world AI applications
Strong prompt engineering skills including Chain-of-Thought, Few-Shot Prompting, and Tree-of-Thought reasoning techniques
Ability to design and optimize prompts to improve response accuracy, reduce latency, and control token cost
Experience creating system prompts with structured outputs (JSON or schema-based) and implementing safety guardrails
Understanding of LLM data preparation including dataset cleaning, formatting & tokenization
Exposure to model adaptation or fine-tuning workflows using modern ML pipelines
Working knowledge of machine learning frameworks such as PyTorch or TensorFlow
Hands-on experience designing and implementing end-to-end Retrieval-Augmented Generation (RAG) pipelines
Exposure to vector databases such as Pinecone, Weaviate, Milvus, or Qdrant
Strong understanding of embeddings, semantic search, and re-ranking strategies
Experience building AI agents or agentic workflows using frameworks such as LangChain, LangGraph, or AutoGPT
Ability to implement tool or function calling that enables LLMs to interact with external APIs, databases, or services