Senior Generative AI / AI Solution Architect
h3Who We Are /h3 pWe operate beyond organizational silos, combining deep expertise in data engineering and AI-driven solutions to design and deliver scalable, user-centric applications and modern data architectures. We support a wide range of industries, including Automotive, Banking, Insurance, Telecommunications, E-commerce, and Public Services. /p pOur focus is on building robust, enterprise-grade data and AI platforms and enabling advanced analytics and AI capabilities across leading cloud ecosystems, including AWS and Microsoft Azure, as well as Microsoft Fabric and the Power Platform. We specialize in designing secure, scalable, high-performance solutions that integrate data platforms, AI models, and Generative AI use cases to deliver real business value. /p h3What You’ll Be Doing /h3 ul liDesign end-to-end architectures for Generative AI, agentic AI, enterprise knowledge solutions, document automation, and intelligent workflows. /li liDefine agent architectures covering orchestration, tools, APIs, state and memory management, retrieval, model routing, human-in-the-loop patterns, observability, and failure recovery. /li liDesign enterprise RAG solutions using semantic and hybrid search, vector and graph-based retrieval, metadata filtering, access controls, citations, reranking, evaluation, and feedback loops. /li liArchitect foundation-model integration and model gateway patterns, including model selection, routing, fallback strategies, prompt and context management, safety controls, latency, and cost-performance optimization. /li liDevelop document intelligence and structured-generation patterns for proposals, reports, validation workflows, and engineering artefacts. /li liDesign scalable serverless, containerized, API-based,
and event-driven solutions across AWS, hybrid, and on-premises environments. /li liDefine security, identity, networking, observability, evaluation, deployment, governance, and LLMOps standards for production AI solutions. /li liBuild prototypes and reference implementations to validate architectural approaches and emerging technologies. /li liReview solution designs and code, resolve critical technical challenges, and provide technical guidance to engineering teams. /li liMentor engineers and contribute to architecture standards, best practices, and technology decisions across projects. /li /ul h3What You’ll Bring Along /h3 ul liAt least 8 years of relevant experience across software engineering, cloud, data, platform engineering, or AI, including significant experience designing enterprise-scale solutions. /li liProven experience designing and delivering production AI and machine-learning solutions. /li liStrong hands-on experience designing and delivering production Generative AI and LLM solutions, including RAG, embeddings, retrieval, evaluation, guardrails, and agentic workflows. /li liStrong software engineering background, preferably with hands-on Python experience and familiarity with one or more additional languages such as Java, C#, TypeScript/JavaScript, Go, or equivalent. /li liStrong understanding of REST, gRPC,
asynchronous processing, event-driven architectures, and enterprise integration patterns. /li liProven architecture experience across public cloud and hybrid, private-cloud, or on-premises environments. /li liHands-on experience with AWS AI and application services, including Amazon Bedrock or comparable foundation-model platforms. /li liExperience designing retrieval architectures using technologies such as Amazon OpenSearch, PostgreSQL/pgvector, vector databases, and/or graph-based retrieval systems. /li liStrong knowledge of IAM, private networking, secrets management, observability, CI/CD, infrastructure as code, AI evaluation, safety, and production LLMOps. /li liStrong understanding of production AI considerations such as scalability, reliability, latency, security, governance, and cost optimization. /li liStrong client-facing consulting and technical communication skills, with the ability to translate complex business requirements into scalable technical solutions. /li liA high degree of ownership, collaboration, technical decision-making, and mentoring capability. /li liExcellent command of both spoken and written English. /li /ul h3Nice to have /h3 ul liExperience with Amazon Bedrock AgentCore, Bedrock Guardrails, AWS Glue, Lambda, ECS, or EKS. /li liExperience with LiteLLM, open-source models, model gateways, or multi-model architectures. /li liExperience with knowledge graphs and graph-based retrieval. /li liExperience with Azure AI or other enterprise AI platforms. /li liExperience designing AI solutions for regulated or security-sensitive environments. /li liRelevant AWS, Azure, AI, cloud, or architecture certifications. /li /ul #J-18808-Ljbffr
and event-driven solutions across AWS, hybrid, and on-premises environments. /li liDefine security, identity, networking, observability, evaluation, deployment, governance, and LLMOps standards for production AI solutions. /li liBuild prototypes and reference implementations to validate architectural approaches and emerging technologies. /li liReview solution designs and code, resolve critical technical challenges, and provide technical guidance to engineering teams. /li liMentor engineers and contribute to architecture standards, best practices, and technology decisions across projects. /li /ul h3What You’ll Bring Along /h3 ul liAt least 8 years of relevant experience across software engineering, cloud, data, platform engineering, or AI, including significant experience designing enterprise-scale solutions. /li liProven experience designing and delivering production AI and machine-learning solutions. /li liStrong hands-on experience designing and delivering production Generative AI and LLM solutions, including RAG, embeddings, retrieval, evaluation, guardrails, and agentic workflows. /li liStrong software engineering background, preferably with hands-on Python experience and familiarity with one or more additional languages such as Java, C#, TypeScript/JavaScript, Go, or equivalent. /li liStrong understanding of REST, gRPC,
asynchronous processing, event-driven architectures, and enterprise integration patterns. /li liProven architecture experience across public cloud and hybrid, private-cloud, or on-premises environments. /li liHands-on experience with AWS AI and application services, including Amazon Bedrock or comparable foundation-model platforms. /li liExperience designing retrieval architectures using technologies such as Amazon OpenSearch, PostgreSQL/pgvector, vector databases, and/or graph-based retrieval systems. /li liStrong knowledge of IAM, private networking, secrets management, observability, CI/CD, infrastructure as code, AI evaluation, safety, and production LLMOps. /li liStrong understanding of production AI considerations such as scalability, reliability, latency, security, governance, and cost optimization. /li liStrong client-facing consulting and technical communication skills, with the ability to translate complex business requirements into scalable technical solutions. /li liA high degree of ownership, collaboration, technical decision-making, and mentoring capability. /li liExcellent command of both spoken and written English. /li /ul h3Nice to have /h3 ul liExperience with Amazon Bedrock AgentCore, Bedrock Guardrails, AWS Glue, Lambda, ECS, or EKS. /li liExperience with LiteLLM, open-source models, model gateways, or multi-model architectures. /li liExperience with knowledge graphs and graph-based retrieval. /li liExperience with Azure AI or other enterprise AI platforms. /li liExperience designing AI solutions for regulated or security-sensitive environments. /li liRelevant AWS, Azure, AI, cloud, or architecture certifications. /li /ul #J-18808-Ljbffr