Ampstek · 5 hours ago
Generative AI / LLM Engineer || Only US Citizen and Green Card Required
Ampstek is seeking a Generative AI / LLM Engineer to join their team. The role involves designing, developing, and optimizing LLM-based solutions while collaborating with cross-functional teams to create AI-driven solutions.
IT Management
Responsibilities
Strong proficiency in Python with hands-on experience in Machine Learning (ML), Natural Language Processing (NLP), and text data analysis
Design, develop, and optimize LLM-based solutions, including prompt engineering, LLM evaluation, and performance tuning
Build and maintain APIs for AI/ML services and integrate them into production systems
Develop and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma)
Apply best practices for LLM evaluation, monitoring, and observability using tools such as LangSmith or similar frameworks
Deploy and manage LLM applications using libraries such as LiteLLM, LLM Guardrails, and related GenAI frameworks
Implement MLOps practices, including CI/CD pipelines, model versioning, automated testing, and scalable model deployment
Collaborate with cross-functional teams to translate business requirements into robust AI-driven solutions
Ensure model reliability, security, and compliance, including guardrails and responsible AI practices
Work with or learn containerization and orchestration technologies such as Docker and Kubernetes
Leverage cloud platforms (AWS, GCP, or Azure) for model training, deployment, and monitoring
Continuously stay updated with emerging GenAI, LLM, and MLOps technologies and recommend improvements
Qualification
Required
Strong proficiency in Python with hands-on experience in Machine Learning (ML), Natural Language Processing (NLP), and text data analysis
Design, develop, and optimize LLM-based solutions, including prompt engineering, LLM evaluation, and performance tuning
Build and maintain APIs for AI/ML services and integrate them into production systems
Develop and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma)
Apply best practices for LLM evaluation, monitoring, and observability using tools such as LangSmith or similar frameworks
Deploy and manage LLM applications using libraries such as LiteLLM, LLM Guardrails, and related GenAI frameworks
Implement MLOps practices, including CI/CD pipelines, model versioning, automated testing, and scalable model deployment
Collaborate with cross-functional teams to translate business requirements into robust AI-driven solutions
Ensure model reliability, security, and compliance, including guardrails and responsible AI practices
Work with or learn containerization and orchestration technologies such as Docker and Kubernetes
Leverage cloud platforms (AWS, GCP, or Azure) for model training, deployment, and monitoring
Continuously stay updated with emerging GenAI, LLM, and MLOps technologies and recommend improvements