AI Expert developer

Responsibilities:
Design, develop, and deploy autonomous and semi autonomous AI agents to automate complex tasks across the software development lifecycle (SDLC).
Design and implement MCP (Model Context Protocol) servers to integrate large language models (LLM) with internal systems, development tools, and enterprise data sources.
Identify acceleration opportunities within the SDLC (code generation, code review, automated testing, documentation, deployment) and design tailored AI solutions.
Develop robust prompt engineering pipelines and agent chains (multi agent orchestration) to solve concrete business problems.
Integrate generative AI solutions (LLM, RAG, agents) with existing DevOps tools (CI/CD, ticketing systems, version control, etc.).
Collaborate with development, architecture, and operations teams to drive the adoption of AI practices within product teams.
Ensure the quality, reliability, and observability of AI agents in production (monitoring, tracing, output evaluation).
Actively monitor technological developments in LLMs, agent frameworks, and integration protocols (MCP, OpenAI function calling, tool use, etc.).
Document architectures, technical decisions, and usage guides for internal teams.
Required Qualifications:
Minimum 5 years of experience in software development, including at least 2 years focused on applied AI/ML.
Hands on experience developing AI agents using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or equivalents.
Proficiency in setting up MCP servers and integrating LLMs via APIs (OpenAI, Anthropic, Azure OpenAI, etc.).
Strong Python experience and solid knowledge of software development best practices (testing, code review, versioning).
Experience with RAG (Retrieval Augmented Generation) architectures and vector databases (Pinecone, Weaviate, pgvector, etc.).
Good understanding of the SDLC and DevOps/MLOps practices (CI/CD, Docker, Kubernetes, Git).
Ability to communicate complex technical concepts to non technical stakeholders.
Bilingual (French and English).
Additional Assets:
Experience with AI powered developer tools: GitHub Copilot, Cursor, Codeium, or similar solutions.
Knowledge of agent integration protocols: MCP (Model Context Protocol), OpenAI Assistants API, tool use (Anthropic).
Experience in LLM evaluation and benchmarking (LLM as a judge, RAGAS, PromptFlow, etc.).
AI/ML certification on a cloud platform (Azure AI Engineer, AWS ML Specialty, GCP Professional ML Engineer).
Experience in a consulting or client project delivery context.