Associate Architect

Job Description

The Hands-On Full-Stack Technology Architect with AI and LLM expertise is a senior technical leader who designs scalable, intelligent systems while actively contributing across the tech stack. This role is ideal for someone who combines modern web and backend development with deep experience in integrating and scaling Large Language Model (LLM) platforms such as OpenAI, Claude, Mistral, or custom models via Hugging Face, AWS Bedrock, or Vertex AI. Key Responsibilities: Architecture Design Define robust, scalable, cloud-native, cloud agnostic architectures for AI platforms Architect and prototype AI systems/platforms Design and document system architecture (component diagrams, API contracts, deployment topology). Champion modern design patterns (microservices, micro frontends, event-driven, DDD, etc). Build composable architecture patterns for integrating LLM APIs with microservices and UI layers. Create end-to-end architectures, build distributions, environments and deploy solutions Hands-On Development Build and integrate reusable components, LLM-enabled APIs, and workflows with stateful orchestration where needed (e.g., using LangChain or semantic pipelines). Develop and iterate on PoCs and reference implementations of LLM-based features. Write maintainable, high-quality code in both frontend (React) and backend (Python ,Node.js, Java, Go) technologies. Build reusable UI components, design systems, and frontend microservices where applicable. Create proof-of-concepts and reference implementations to de-risk architectural decisions. Contribute to CI/CD automation, DevOps pipelines, and infrastructure-as-code setups (Terraform, Helm). Frontend Engineering Architect and implement responsive UIs with state management (Redux, Zustand, or similar). Integrate RESTful and GraphQL APIs, implement frontend performance tuning and security best practices (XSS, CSP, etc). Define and enforce front-end development standards and reusable design patterns. LLM Engineering Integration Integrate LLMs via OpenAI, Claude, Mistral, Vertex AI, or AWS Bedrock APIs. Apply techniques like prompt engineering, embeddings, RAG (retrieval-augmented generation), and fine-tuning where applicable. Design and implement vector database-backed search pipelines using Pinecone, FAISS, Weaviate, or Vespa. Collaborate with data scientists and MLOps teams to bring custom LLMs to production securely and reliably. Team Collaboration Leadership Work with product owners, UX/UI designers, QA, and devs across teams to shape and implement feature architecture. Mentor engineers across levels through pair programming, design reviews, and architectural guidance. Participate in sprint planning, story breakdowns, and estimation with a technical mindset Lead data science projects from conception to deployment, ensuring timely and successful delivery. Partner with BU teams in driving the collaboration mandates Communication: Effectively communicate findings and recommendations to both technical and non-technical audiences. Required Skills and Qualifications: Engineering Hands on proficiency in Design and Architecture of the platforms Good awareness of the design patterns implementation experience Handson Proficiency in JavaScript/TypeScript, Python, or Go. Experience with React or Angular on the frontend. REST/GraphQL API design and integration. Familiarity with event-driven architectures and async processing (Kafka, RabbitMQ,etc).Microservices Strong with AWS/ Azure, containerization (Docker, Kubernetes), and Infrastructure-as Code . Must have worked on the production-ready solutions and be abreast with the scaling and complexity solutions involved in creating enterprise solutions. LLM AI Platforms Experience integrating LLM APIs (OpenAI, Claude, Mistral, Cohere, etc). Knowledge of LangChain, LlamaIndex, or Semantic Kernel for orchestration. Hands-on with embeddings, vector databases (Pinecone, FAISS, etc), and prompt engineering. Familiarity with AI/ML deployment platforms (SageMaker, Vertex AI, Hugging Face, etc)