Remote-Senior Software Engineer-Intuit
This position is posted by Jobgether on behalf of S M Software Solutions Inc. We are currently looking for a Senior Software Engineer in United States.
We are seeking a Senior Software Engineer specializing in Retrieval-Augmented Generation (RAG) systems, large language models (LLMs), and scalable cloud-based microservices. This role focuses on designing, integrating, and optimizing LLM workflows to deliver high-accuracy data retrieval and advanced content generation. You will work closely with engineering peers to build containerized applications, manage vector databases, and leverage AWS cloud services for robust, serverless solutions. Ideal candidates are problem-solvers who thrive in remote or hybrid environments, enjoy working with cutting-edge AI technologies, and can translate complex architectures into efficient, maintainable systems. Your contributions will directly enhance data-driven applications and impact enterprise-scale AI workflows.
Accountabilities
· Design, deploy, and optimize RAG workflows using LangChain and vector databases for high-accuracy retrieval and intelligent content generation.
· Integrate and manage vector databases such as Qdrant to support efficient, large-scale data searches.
· Develop serverless and containerized applications using AWS services including Lambda and ECS.
· Build APIs with FastAPI and Uvicorn to ensure low-latency, high-throughput interactions.
· Implement monitoring and observability practices using tools like Datadog and ddtrace to troubleshoot complex workflows and maintain system performance.
· Collaborate with cross-functional teams to align on architecture, deployment strategies, and operational best practices.
· Proven experience with LLMs, RAG workflows, LangChain, and vector databases.
· Advanced Python skills (versions >=3.11, Apply Now
Apply Now
We are seeking a Senior Software Engineer specializing in Retrieval-Augmented Generation (RAG) systems, large language models (LLMs), and scalable cloud-based microservices. This role focuses on designing, integrating, and optimizing LLM workflows to deliver high-accuracy data retrieval and advanced content generation. You will work closely with engineering peers to build containerized applications, manage vector databases, and leverage AWS cloud services for robust, serverless solutions. Ideal candidates are problem-solvers who thrive in remote or hybrid environments, enjoy working with cutting-edge AI technologies, and can translate complex architectures into efficient, maintainable systems. Your contributions will directly enhance data-driven applications and impact enterprise-scale AI workflows.
Accountabilities
· Design, deploy, and optimize RAG workflows using LangChain and vector databases for high-accuracy retrieval and intelligent content generation.
· Integrate and manage vector databases such as Qdrant to support efficient, large-scale data searches.
· Develop serverless and containerized applications using AWS services including Lambda and ECS.
· Build APIs with FastAPI and Uvicorn to ensure low-latency, high-throughput interactions.
· Implement monitoring and observability practices using tools like Datadog and ddtrace to troubleshoot complex workflows and maintain system performance.
· Collaborate with cross-functional teams to align on architecture, deployment strategies, and operational best practices.
· Proven experience with LLMs, RAG workflows, LangChain, and vector databases.
· Advanced Python skills (versions >=3.11, Apply Now
Apply Now