Senior LLM Engineer

About Us At micro1, were all about connecting skilled remote professionals with some of the best companies in Silicon Valley Our mission is to offer a stable, competitive income, along with access to top industry opportunities?all in a flexible work setting with a range of great benefits Were here to help you grow in your career We're proud to work with trusted partners such as Deel, Immutable, OGara, and LegalSoft What We Offer Healthcare reimbursement Wi-Fi Reimbursement Unlimited Learning: Access to Udemy courses, books, and everything you need to keep growing And So Much More: Were not just about work?were about creating an environment where youll love to be! About The Role We are seeking a Senior Large Language Model (LLM) Engineer with solid experience in production deployments The ideal candidate will have a proven track record in developing, deploying, and optimizing large language models in a production environment We are looking for individuals who have hands-on experience and are capable of managing end-to-end solutions rather than just building prototypes or proofs of concept Key Responsibilities Design, develop, and deploy large language models for diverse, production-level applications Scale GenAI applications to handle high user loads and large datasets with optimized response times Develop and refine prompt strategies, including zero-shot and context-based techniques, for effective LLM utilization Set up and manage end-to-end pipelines involving vector databases, caching layers, and embedding systems Work in containerized environments, such as Kubernetes, to build and maintain pipelines and create API endpoints Required Qualifications 4-8 years of Experience in software engineering, with at least 2 years in hands-on LLM projects 3-4 years of experience in Python Development, with proficiency in FastAPI or Flask Strong understanding of APIs , WebSockets, and production deployments Experience with EC2, SageMaker, and AWS databases in AWS Services Hands-on experience with frameworks such as Langchain, LlamaIndex, DSPy, and tools like OpenAI, vector databases, and recent prompt engineering and RAG implementations in LLM/GenAI Expertise Proficiency in setting up pipelines, containerizing applications, and creating handoff-ready API endpoints for DevOps in Kubernetes Practical experience with fine-tuning open-source models for production environments Nice To Have Familiarity with Azure services Practical and deployed experience rather than hobbyist projects Experience in Fine-Tuning Open Source Models