Full Stack Engineer - GenAI & LLM
Experience: 5 - 20 Years
Location: North America - Permanent Remote
Must-Have
• Experience with Microsoft OpenAI Azure or Google Vertex
• Experience developing GenAI applications (doesn't have to be professional)
• End-to-end full-stack application development
• Experience developing API endpoints in Python or Java
• Experience with PyTorch and/or TensorFlow
• Experience working with multiple AI Frameworks (hugging face, semantic search, RAG, etc)
Platform / Stack
You will work with technologies that include Microsoft OpenAI Azure, Google Vertex, PyTorch, and RAG Architecture.
What You'll Do As a Sr Software Engineer
• Architect, design, and develop AI applications, integrating with Google Vertex, Microsoft OpenAI Azure, and other LLM suites
• Design and implement effective prompts, configure LLM settings, and optimize performance through prompt crafting, RAG, fine-tuning and other techniques
• Collaborate with cross-functional teams to define requirements, manage user expectations, and deliver high-quality AI solutions
• Develop and maintain API endpoints, front-end features, and full-stack applications that leverage LLMs and Generative AI models
• Implement AI applications that comply with ethical guidelines and legal standards, particularly regarding data privacy and user consent
• Integrate analytics and monitoring tools to track user interactions, application performance, and the efficiency of LLM integrations
• Mentor, motivate, and develop the technical capabilities of the existing engineering team
• Stay up-to-date with emerging trends and advancements in Generative AI, LLMs, and related technologies
Qualifications
You could be a great fit if you have:
• 8+ years of experience in full-stack software development, with a strong focus on building enterprise-scale distributed and cloud or hybrid-cloud applications
• Regarded as an expert in the growing field of AI with 5+ years of experience developing AI solutions and prototypes, including Generative AI and LLMs
• Experience with PyTorch, TensorFlow, ONNX, LangChain, Kubernetes, and Docker
• Deep understanding of AI frameworks including Huggingface, semantic search, RAG, LLM agents, AgentGPT, orchestration, plugins, and LLM Ops
• Experience with Retrieval-Augmented Generation (RAG) architectures or frameworks like Langchain for building LLM-powered applications
• Proficiency in programming languages such as Python, Java, JavaScript, and experience with frameworks like React and Node.js
• Experience with cloud platforms such as Google Vertex, Microsoft OpenAI Azure, AWS, and Azure, using various solutions for developing integrations, APIs, and AI/ML applications
Skills: hybrid-cloud applications,azure,api,api endpoints in python,analytics and monitoring tools,cloud platforms,full-stack application development,llms,aws,distributed and cloud,huggingface,microsoft,legal standards,generative ai,langchain,ethical guidelines,google vertex,cloud or hybrid-cloud applications,python,javascript,pytorch,retrieval-augmented generation (rag) architectures,google,kubernetes,docker,onnx,api development,node.js,cloud,full-stack software development,java,microsoft openai azure,semantic search,rag,hugging face,distributed and cloud application development,programming languages,programming languages (python, java, javascript),llm suites,vertex,api endpoints in java,llm-powered applications,enterprise-scale distributed and cloud or hybrid-cloud applications,llm integrations,ai frameworks,react,cloud platforms (google vertex, microsoft openai azure, aws, azure),genai applications,enterprise-scale distributed and cloud applications,api endpoints,tensorflow,ai solutions and prototypes
Location: Washington, DC
Posted: Oct. 14, 2024, 8:31 a.m.
Apply Now Company Website