Gen AI Principal Consultant

Job DescriptionJob Summary: We are seeking a highly skilled and experienced Gen AI Architect/ Principal Consultants to lead our Generative AI Technologies team.

Veuillez postuler rapidement si vous correspondez bien à ce poste, en raison du grand nombre de candidatures attendues.

The ideal candidate will have a deep understanding of Generative and Agentic AI, LLMs, retrieval-augmented generation (RAG), machine learning, and modern interoperability standards such as the Model Context Protocol (MCP), along with a proven track record of architecting and implementing innovative, enterprise-scale solutions.

As a Gen AI Architect/ Principal Consultants, you will play a pivotal role in shaping our Generative AI strategy, selecting appropriate models and technologies, and collaborating with cross-functional teams to deliver cutting-edge solutions that meet customer requirements and business objectives.Primary Skill Set:Generative AI Expertise: In-depth knowledge of modern Generative AI techniques and foundation models, including transformer-based Large Language Models (LLMs), diffusion models, and multimodal models, as well as earlier architectures such as GANs (Generative Adversarial Networks) and VAEs (Variational Autoencoders).

Experience across text, code, image, and multimodal generation is essential.

Conversant with modern Gen AI development techniques and tooling such as advanced prompt engineering, structured outputs, function/tool calling, and orchestration frameworks like LangChain, LangGraph, LlamaIndex, and Semantic Kernel.

Hands-on exposure to both API-based (e.g., Claude, GPT, Gemini) and open-source (e.g., Llama, Mistral) LLM-based solution design.

Agentic AI & Multi-Agent Architecture: Deep expertise designing autonomous and multi-agent systems that reason, plan, and act using tools.

Command of agentic design patterns (e.g., ReAct, planning, reflection, tool use, human-in-the-loop) and agent frameworks such as LangGraph, CrewAI, MAF, the OpenAI Agents SDK, and Google’s Agent Development Kit (ADK).

Proven ability to architect reliable agentic workflows with memory, state management, orchestration, and safe multi-step task execution at scale.Model Context Protocol (MCP) & Interoperability: Strong working knowledge of the Model Context Protocol (MCP) for standardized, secure connectivity between LLMs/agents and enterprise tools, data sources, and systems.

Ability to architect, build, and govern MCP servers and clients and to work with MCP primitives such as tools, resources, and prompts.

Awareness of related interoperability standards (e.g., agent-to-agent communication) for composing scalable, enterprise-grade agentic ecosystems.Agent Skills & Extensibility: Experience extending agent capabilities through modular, reusable skills—packaged instructions, scripts, and resources (e.g., -style capability modules) loaded on demand via progressive disclosure.

Ability to define standards for custom tools, connectors, and skills that let agents perform specialized, domain-specific tasks reliably, securely, and consistently across teams.Retrieval-Augmented Generation (RAG) & Knowledge Architecture: Expertise architecting RAG and knowledge-grounded systems—chunking strategies, embeddings, vector databases (e.g., Pinecone, Weaviate, Chroma, pgvector, FAISS), hybrid search, reranking, and retrieval evaluation.

Familiarity with advanced patterns such as GraphRAG and agentic RAG to maximize factual grounding and minimize hallucination in production.LLMOps, Evaluation & Responsible AI: Experience operationalizing LLM and agentic systems at scale—evaluation harnesses and metrics for quality, groundedness, and safety; observability, tracing, and monitoring (e.g., LangSmith, LangFuse); guardrails and red-teaming; and continuous optimization of accuracy, cost, and latency.

Understanding of AI governance, security, privacy, bias/fairness, and emerging AI regulation.Machine Learning Mastery: Profound understanding of machine learning principles, algorithms, and frameworks.

Able to design and implement models, optimize performance, and manage training pipelines effectively.Technical Proficiency: Proficiency in programming languages commonly used in AI development, such as Python, TensorFlow, PyTorch, or similar tools, along with modern LLM/agent frameworks (LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, AutoGen).

Experience with cloud AI platforms (e.g., Amazon Bedrock, Azure OpenAI / AI Foundry, Google Vertex AI), vector databases (e.g., Pinecone, Weaviate, Chroma, pgvector, FAISS), containerization and orchestration (Docker, Kubernetes), and distributed computing is advantageous.Architecture Design: Ability to design end-to-end Generative and Agentic AI architectures that encompass data preprocessing, model selection, RAG pipelines, agent orchestration, MCP-based tool and system integration, guardrai