.The Product Architect owns all technical matters related to their assigned products, with a focus on creating AI-powered tools that enhance existing product capabilities.
This includes designing and orchestrating feature implementations for AI-driven functionalities; maintaining, guiding, and improving the architectural integrity of these AI enhancements; and ensuring best practices and architectural guidelines are followed across the AI and machine learning domains.
Familiarity with TestRail or similar software testing tools is a plus.Responsibilities:Develop a deep understanding of both the product code base and AI tools, including LLM applications, through hands-on experimentation and explorationDesign and implement AI-powered tools that integrate seamlessly with existing product workflowsAssess and shepherd the technical delivery of AI enhancements to ensure adherence with best practicesDrive continual improvement of development processes, with an emphasis on machine learning pipelines and LLM trainingCollaborate with the Product Management Team and other stakeholders, contributing to the product roadmap, product requirements, and product release scheduleIdentify gaps in the technical aspects of the end user experienceEstimate software development requirements and effort, propose alternatives, and prioritize development tasks for a given areaGeneral requirements:Bachelor's or Master's degree in Computer Science, Engineering, or a related field4+ years of experience in software engineeringHands-on experience in building and deploying AI/ML solutions in productionStrong experience in Natural Language Processing (NLP) with LLMsStrong understanding of API development for integrating AI solutions.Experience with Retrieval-Augmented Generation (RAG), LlamaIndex, and LangChainExperience with cloud platforms (AWS)Experience with fine-tuning LLMs.Proficiency in Ruby (must-have), TypeScript (nice to have) and Python (nice to have)- Familiarity with MLOps best practices, including:Model deployment, monitoring, and versioning.Model lifecycle management.- Ability to build scalable and efficient AI pipelines.- Understanding of data engineering best practices (ETL pipelines, data lakes).- Knowledge of data processing techniques, including:Preprocessing text and unstructured data for NLP applicationsUsing embeddings for LLM-based applications.System Design & Best Practices:Experience designing scalable and cost-effective AI architectures that handle real-world constraints.Strong knowledge of performance optimization for AI-driven applications.Understanding of security and compliance in AI solutions.Experience working with containerization (Docker, Kubernetes) for AI model deployment.Collaboration & Documentation:- Ability to create documentation that communicates:Business-level understanding of AI solutions.Technical implementation details for developers and engineers