Senior Software Engineer, Full-Stack (Copy)

About Doowii Doowii is building a conversational analytics platform for education. We enable non-technical users to query complex datasets using natural language, accelerating decision making, data exploration, and intervention planning. Doowii sits at the intersection of data infrastructure, AI, and education. About the Role We are seeking strong full-stack engineers who are proficient in web frameworks, backend development, and infrastructure. As an Applied AI Software Engineer, you'll help design, build, evaluate, and operate the AI-powered systems that transform natural language into actionable insights. Applicants must demonstrate technical mastery, architectural skills, mentoring abilities, and independence. You'll work across Doowii's tech stack, from LLM orchestration and retrieval systems to backend APIs, data pipelines, and customer-facing product experiences. What You’ll Work On Doowii engineering is critical in the end-to-end development of the Doowii platform, applications, and systems, from designing the user interface to managing our systems and infrastructure.  AI Systems & Product Development Design and implement AI-powered product capabilities using large language models, embeddings, retrieval systems, and agent workflows Build and maintain evaluation frameworks to measure AI quality, accuracy, reliability, and customer impact Improve prompt strategies, tool usage, retrieval quality, and agent behavior Develop systems for semantic search, retrieval-augmented generation (RAG), and conversational analytics Experiment with new models, frameworks, and AI techniques to improve platform capabilities Partner with product and engineering teams to translate customer needs into AI-driven solutions Backend & Platform Engineering Build scalable backend services and APIs that support AI workflows and customer-facing applications Design and maintain services that orchestrate LLM interactions, retrieval systems, and external tools Develop and optimize data processing workflows that support AI-powered experiences Improve observability, reliability, testing, and deployment practices for AI systems Contribute to architecture decisions across application, infrastructure, and data layers Data & Retrieval Infrastructure Build and maintain retrieval pipelines, embedding workflows, and vector search systems Design data models and indexing strategies that improve AI accuracy and performance Work with structured and unstructured datasets to support analytics and natural-language experiences Optimize storage, retrieval latency, and evaluation workflows Full-Stack Collaboration Contribute to frontend and user-facing product features when needed Partner closely with frontend, backend, data, and product teams Help shape the user experience of AI-powered features and workflows Requirements Bachelor's degree in Computer Science, Engineering, Machine Learning, Data Science, or related field (or equivalent practical experience) 3+ years of professional software engineering experience Strong proficiency in Python Experience building and maintaining production software systems Experience working with LLM APIs and modern AI application frameworks Experience implementing retrieval, embeddings, vector search, or RAG workflows Experience designing APIs and backend services Strong SQL and data modeling skills Experience with cloud platforms such as AWS, GCP, or Azure Experience evaluating AI system quality, reliability, or performance Strong problem-solving skills and comfort working across multiple technical domains Bonus points if you have: Masters in computer engineering Experience in any of the following areas: building agent-based systems or tool-calling workflows developing LLM evaluation frameworks, automated testing, or benchmark systems fine-tuning models or working with open-weight models working with vector databases such as Pinecone, Weaviate, pgvector, OpenSearch, or equivalent building analytics platforms or data-intensive applications working with Airflow, Dagster, dbt, Kafka, Spark, Iceberg, ClickHouse, BigQuery, or Snowflake managing complex workflows with prompt engineering, structured outputs, and AI safety/reliability techniques working with conversational interfaces, search systems, or natural-language-driven products