Duties

• Design, develop, and maintain full-stack AI-driven web applications and microservices using Python, Java, and React, delivering both high-quality prototype systems and production-ready applications that meet performance and reliability standards.

• Build, deploy, and optimize RESTful API backend services using FastAPI and Flask frameworks; implement and consume APIs across distributed application layers to support real-time document processing and large-scale data pipelines.

• Develop and maintain frontend user interfaces using React, including researcher dashboards, administrative consoles, and data visualization components, applying user interaction best practices.

• Integrate large language model (LLM) APIs and retrieval-augmented generation (RAG) pipelines — including prompt engineering, cost optimization, hallucination heuristics, and output evaluation — into production software systems to enable intelligent document processing, semantic search, and automated generation capabilities.

• Design and implement data storage, retrieval, and management solutions using relational databases (PostgreSQL, MySQL) and NoSQL databases (MongoDB); manage document-scale data operations and data integrity across large corporations.

• Deploy, manage, and monitor containerized microservice applications on AWS cloud infrastructure using Docker, applying scalability and operational efficiency best practices across development and production environments.

• Collaborate with AI researchers, product managers, designers, and cross-functional engineering teams to design and implement human-AI workflow tools and applied AI research products, owning end-to-end development of key platform components.

Requirements

• This position requires a Bachelor27s degree or equivalent in Computer Science, Computer Engineering, Information Technology, or a closely related field and 3 years of experience in using full-stack AI software development, including AI frameworks, backend API development and frontend development using modern web frameworks.

Must also have each of the following:

• Demonstrated experience working with Python for backend development, data processing, and machine learning or NLP workflow implementation.

• Demonstrated experience with developing backend service with Java or equivalent object-oriented programming language.

• 3 years of demonstrated frontend development experience with JavaScript, of which 2 years must be in React, including component design and integration with REST APIs.

• 2 years of demonstrated experience working in backend framework with FastAPI and/or Flask for building and deploying RESTful web services.

• 2 years of demonstrated experience designing, implementing, and consuming RESTful APIs across distributed application architectures.

• 3 years of demonstrated experience working with relational database systems (PostgreSQL and/or MySQL) and NoSQL databases (MongoDB) for structured and unstructured data management.

• Demonstrated experience implementing search and information retrieval solutions using Elasticsearch.

• 2 years of demonstrated experience integrating LLM APIs and RAG pipeline frameworks, including Langchain, into production AI applications.

• Demonstrated experience working with NLP techniques including named entity recognition (NER), text classification, and topic modeling, using libraries such as NLTK, SpaCy, or Scikit-Learn.

• 2 years of demonstrated experience working and collaborating with AI researchers to develop and deploy AI models into production systems.

• Demonstrated experience containerizing and deploying applications using Docker on AWS cloud infrastructure, including AWS S3.

• Employer will accept experience gained concurrently.

• Salary: $137,717 to $160,000/year.

• Full-time, position located in New York, NY.

• Please apply online at .