GenAI/AI-ML Engineer - On-Premises LLMs
Core
Design and implement generative AI solutions using LLMs on on-premises infrastructure, developing production-grade Python services and applications.
Role type
Senior IC GenAI/AI-ML Engineer
Builds
Production-grade Python services, chatbots, retrieval pipelines, and text generation solutions
Domain
Generative AI, On-Premises LLMs, RAG
Deliverable
production ML models
Required skills
Python, LangChain, LangGraph, Streamlit, NLP, Data Preprocessing, Feature Engineering, Embeddings, Vector Databases, SOLR, Lucene
Preferred skills
On-premises LLM stack deployment, RAG pipelines, Agile delivery, CI/CD for ML
Technologies
Python, LangChain, LangGraph, Streamlit, Solr, Lucene, RAG, LLM, AI CI/CD
Responsibilities
Design and implement generative AI solutions using LLMs on on-premises infrastructure; Develop production-grade Python services and applications; Create and refine prompts, retrieval pipelines, and chatbots; Preprocess data and engineer features including embeddings and vector databases; Deploy, monitor, and optimize models and services in production environments.
