Sr. AI Architect

Overview

LABUR is partnering with a client to identify a Senior AI Architect who will lead the design, development, and delivery of an enterprise-scale agentic AI platform built on AWS. This hands-on architect will own both the blueprint and the build, shaping LLM-powered assistants, RAG pipelines, and agent-based systems while translating complex business problems into scalable technical solutions. Working closely with business stakeholders, this individual will identify high-value use cases, drive platform adoption, and establish governance and best practices across the AI portfolio, balancing speed, quality, and scalability at every stage.

Responsibilities

• Lead the design and hands-on implementation of an enterprise agentic AI platform leveraging AWS Bedrock, AgentCore, and foundation models including Claude, Amazon Titan, and OpenAI models available through Bedrock

• Architect and build RAG pipelines end to end, covering ingestion, embeddings, vector indexing, and semantic search optimization for performance and relevance

• Develop LLM-powered assistants and copilots that execute real-world workflows such as customer support automation, knowledge summarization, and enterprise search using agentic AI frameworks like LangChain Agents and Bedrock Agents

• Engage directly with business stakeholders to understand requirements, identify high-value use cases, and translate them into well-scoped technical solutions built on the agentic platform

• Define and enforce reference architectures, reusable components, and best-practice artifacts to ensure consistency, maintainability, and scalability across AI initiatives

• Establish and drive LLMOps practices covering prompt and model versioning, agent lifecycle management, feedback loops, and continuous evaluation

• Ensure AI solutions adhere to regulatory and validation standards (e.g., FDA validation for AI software), internal governance, security protocols, and responsible AI principles

• Mentor engineering teams on generative AI techniques, fine-tuning, prompt engineering, ethics, and explainability while rapidly prototyping new agentic and multimodal workflows to validate feasibility

Qualifications

• 10+ years of professional experience including 7+ years in software engineering and AI/ML, with 3+ years specializing in Generative AI and LLMs

• Proven track record designing, deploying, and scaling enterprise AI/LLM solutions with a hands-on approach to both architecture and implementation

• Strong expertise with AWS services (Bedrock, AgentCore, Lambda, S3, ECS, SageMaker) and direct experience building agentic platforms on AWS infrastructure

• Deep knowledge of GenAI toolchains including LangChain, LlamaIndex, and multi-agent orchestration frameworks

• Extensive experience with vector search, embeddings, retrieval pipelines, and RAG architectures including chunking, indexing, and orchestration strategies

• Proficiency in MLOps/LLMOps practices including CI/CD, model and version management, observability, and monitoring production AI systems (e.g., Datadog, MLflow)

• Solid understanding of enterprise security, compliance, data governance, AI ethics, explainability, and bias mitigation for AI systems

• Proficiency in Python, FastAPI, and WebSockets with excellent communication skills and demonstrated ability to distill complex business requirements into scalable AI solutions

Compensation

$85-$100/hour