Principal Architect – GenAI

This is a fully remote position, open to applicants in Canada.

📋 Description

• In the role of Principal Architect: Gen AI/ Practice Lead - Gen AI at Quantiphi, you will take charge of designing and developing sophisticated machine learning models and algorithms to address intricate business challenges.

• Your responsibilities will include optimizing and deploying these models on AWS infrastructure, ensuring they are scalable and reliable.

⛳️ Requirements

• Over 10 years of substantial hands-on technical experience in the implementation and development of cloud ML solutions on AWS.

• Practical experience with AWS services.

• Demonstrated proficiency with AWS Sagemaker and Bedrock, utilizing various types of data sources, training jobs, and both real-time and batch applications.

• Design and execute agentic AI architectures using frameworks like LangChain and Strand Agents, facilitating autonomous task planning, decision-making, and multi-step reasoning.

• Hands-on experience with Amazon AgentCore for the construction, deployment, and scaling of production-grade agentic AI applications, encompassing agent memory management, tool registry, and observability.

• Architect and deploy scalable AI solutions on AWS, utilizing services such as Lambda, Bedrock, Step Functions, S3, API Gateway, and SageMaker.

• Skilled in working with LLM APIs (e.g., Claude, Nova, and other third-party LLM providers), including API integration and multi-model orchestration strategies.

• Practical experience in fine-tuning or optimizing large language models (LLM).

• Familiarity with LLM tool usage, prompt templating, and context management.

• Strong expertise in Vector Databases, including indexing strategies, embedding generation, similarity search, and integration with RAG architectures.

• Model Evaluation & Optimization: Assess LLM's zero-shot and few-shot capabilities, fine-tuning hyperparameters, ensuring task generalization, and exploring model interpretability for robust web app integration.

• Develop and sustain Model Context Protocol (MCP) implementations to manage state, context windows, memory, and prompt orchestration across distributed agent systems.

• Experience with at least one of the workflow orchestration tools such as Airflow, StepFunctions, SageMaker Pipelines, or Kubeflow.

• Experience in implementing secure, scalable APIs and integrating with third-party data sources and tools.

• Ability to work collaboratively with cross-functional teams, including Developers, QA, Project Managers, and other stakeholders, to comprehend their requirements and execute solutions.

• Must have experience with Deep Learning Concepts such as Transformers, BERT, Attention models, tokenization, and embeddings.

• Experience in software development with exposure to front-end and back-end frameworks and communication protocols.

• Experience in Infrastructure as Code (IaC) and CI/CD pipelines.

• Familiarity with NLP concepts including syntactic/semantic analysis and NER.

🏝️ Benefits

• Become a part of one of the world’s fastest-growing AI-first digital engineering companies and have a tangible impact at scale.

• Lead and collaborate with a dynamic team of talented, motivated individuals tackling complex and meaningful challenges.

• Engage with Fortune 500 companies and innovative disruptors in a research-driven environment with over 60 patents.

• Stay at the forefront by acquiring hands-on experience with state-of-the-art AI, ML, data, and cloud technologies while continuously enhancing your skills.