Entry-Level Generative AI Engineer | LLMs & RAG

Emonics LLC; Austin (TX); On-site; USD 120,000 - 160,000; Full time

Job summary

Emonics LLC is seeking an AI-focused software engineer with a strong foundation in Python, ML, and NLP. You will collaborate with the engineering team to build, integrate, and optimize AI-powered solutions for real-world business challenges in Austin, TX.

The role emphasizes hands-on development with Generative AI, LLMs, and retrieval-augmented generation, including working with APIs like OpenAI, Google Gemini, and Hugging Face.

Qualifications

• Bachelor's degree in Computer Science, IT, AI, or related field.
• Proficiency in Python programming.
• Fundamentals of ML, Deep Learning, and NLP.
• Familiarity with LLMs and Generative AI concepts.
• Basic knowledge of Prompt Engineering.
• Understanding embeddings, vector databases, and semantic search.
• Strong analytical, problem-solving, and communication skills.

Responsibilities

• Develop Generative AI applications using LLMs.
• Integrate LLM APIs (OpenAI, Gemini, Hugging Face).
• Design Retrieval-Augmented Generation (RAG) pipelines.
• Experiment with prompt engineering for better responses.
• Build AI-powered chatbots, assistants, and automation.
• Work with LangChain and LlamaIndex frameworks.
• Integrate vector databases like FAISS, ChromaDB, Pinecone.
• Test, evaluate, and optimize LLM-based solutions.
• Collaborate with software and data science teams.
• Keep up-to-date with new Generative AI tools and trends.

Skills

Python

NLP concepts

Generative AI

Prompt engineering

LLMs & embedding fundamentals

Communication

Education

Bachelor's degree in CS/AI/IT or related field

Tools

OpenAI APIs

Google Gemini

Hugging Face models

LangChain

LlamaIndex

FAISS

ChromaDB

Pinecone

Job description

Emonics LLC is seeking an AI-focused software engineer with a strong foundation in Python, ML, and NLP. You will collaborate with the engineering team to build, integrate, and optimize AI-powered solutions for real-world business challenges in Austin, TX.

The role emphasizes hands-on development with Generative AI, LLMs, and retrieval-augmented generation, including working with APIs like OpenAI, Google Gemini, and Hugging Face.