<p>We are looking for a highly skilled and motivated Software Engineer 3 to join our team, focused on building scalable, efficient, and intelligent systems that integrate with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, and orchestration frameworks. You will play a critical role in designing and implementing intelligent workflows that combine traditional software engineering principles with cutting-edge AI technologies.</p> <p>Key Responsibilities</p> <ul> <li>Design, develop, and maintain software components that integrate Large Language Models (LLMs) into scalable services and applications </li><li>Collaborate with senior engineers, product managers, and data scientists to translate business requirements into LLM-powered features and tools </li><li>Implement and optimize LLM orchestration workflows using frameworks like LangChain, LlamaIndex, or custom-built logic </li><li>Develop and refine prompt strategies for specific use cases, including experimentation with zero-shot, few-shot, and chain-of-thought prompting </li><li>Integrate vector databases and RAG (retrieval-augmented generation) pipelines to enable context-aware AI applications </li><li>Write clean, maintainable, and testable code in Python, following best practices and participating in code reviews and peer programming </li><li>Contribute to the deployment and scaling of applications using Docker, Kubernetes CI/CD pipelines, and cloud infrastructure (e.g., AWS, GCP, or Azure) </li><li>Monitor system performance and work with senior engineers to troubleshoot and resolve production issues related to LLM usage and integration </li><li>Stay current with advancements in LLMs, prompt engineering, and orchestration tools, and help evaluate and recommend new tools or libraries </li><li>Participate in Agile development ceremonies (sprint planning, standups, retrospectives) and contribute to continuous team improvement </li></ul> <p>Education and Experience:</p> <ul> <li>Bachelor's degree in computer science, software engineering, or a related technical field </li><li>4 years of professional software development experience, ideally building scalable APIs, services, or backend systems </li></ul> <p>Skills:</p> <ul> <li>Proficiency in Python and strong coding fundamentals, with experience working in production environments </li><li>Experience with building and integrating LLM-based systems, including hands-on use of APIs from platforms like Azure OpenAI, AWS Bedrock, or Google Gemini </li><li>Familiarity with prompt engineering techniques such as zero-shot, few-shot, chain-of-thought prompting, and task-specific prompt templating </li><li>Understanding of how to orchestrate LLM workflows using frameworks and tools like LangChain, LlamaIndex, or similar orchestration layers </li><li>Experience working with vector databases (e.g., FAISS, Pinecone, Weaviate) and integrating retrieval-augmented generation (RAG) techniques into applications </li><li>Exposure to cloud platforms such as AWS, GCP, or Azure, and basic understanding of deploying applications using containers on Kubernetes </li><li>Experience working with version control (Git) and participating in team-based Agile development workflows (e.g., sprint planning, code reviews, CI/CD) </li><li>An eagerness to learn and apply new technologies in the rapidly evolving LLM and AI tooling ecosystem </li><li>Strong communication skills and the ability to collaborate across functions, document clearly, and contribute meaningfully to discussions </li><li>Experience working with web frameworks (e.g., FastAPI, Flask, Express) or contributing to full-stack applications involving LLMs </li></ul> <p>Soft Skills:</p> <ul> <li>Strong communication skills with the ability to translate complex technical concepts to non-technical audiences. </li><li>Proven ability to influence cross-functional teams without direct authority. </li></ul>