Hybrid Generative AI Engineer: LLMs, RAG & API Dev

EdgeQ Technologies Private Limited; New York (NY); Hybrid; USD 130,000 - 180,000; Full time

Job summary

Appsierra Group is seeking a Generative AI Engineer to design and deploy cutting-edge AI solutions using Python, LLMs, and RAG technologies. The role offers a hybrid work environment across multiple US locations.

You will design, develop, and deploy generative AI applications, build LLM-powered solutions, and create RAG pipelines while integrating LLM APIs, embeddings, and vector databases. Collaborative teamwork and strong problem-solving skills are essential.

Qualifications

• 1–5 years of professional experience in AI/ML, generative AI, or software engineering
• Strong proficiency in Python
• Hands-on experience with Large Language Models (LLMs)
• Experience building Retrieval-Augmented Generation (RAG) applications
• Excellent problem-solving and communication skills

Responsibilities

• Design, develop, and deploy generative AI applications using Python and modern AI frameworks
• Build LLM-powered solutions for enterprise and customer-facing use cases
• Create Retrieval-Augmented Generation (RAG) pipelines for context-aware AI responses
• Integrate LLM APIs, embeddings, vector databases, and external data sources
• Optimize prompts, retrieval strategies, model performance, and response quality
• Develop production-ready APIs and AI services
• Monitor and evaluate model performance in deployed applications
• Collaborate with software engineers, data scientists, and product teams

Skills

Python

LLMs

RAG apps

AI/ML experience

Problem solving

Communication

Tools

OpenAI API

Anthropic API

Gemini API

Pinecone

Weaviate

Chroma

FAISS

FastAPI

Docker

AWS

Azure

GCP

Job description

Appsierra Group is seeking a Generative AI Engineer to design and deploy cutting-edge AI solutions using Python, LLMs, and RAG technologies. The role offers a hybrid work environment across multiple US locations.

You will design, develop, and deploy generative AI applications, build LLM-powered solutions, and create RAG pipelines while integrating LLM APIs, embeddings, and vector databases. Collaborative teamwork and strong problem-solving skills are essential.