Remote Generative AI Engineer: LLMs, RAG & AI Apps

Success Recruitments; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Remote-work support

Equity opportunities

Medical, dental, vision insurance

Paid time off

Job summary

Success Recruitments is seeking an experienced Generative AI Engineer to design, develop, and deploy AI-powered applications for enterprise environments. You will work on LLMs, GenAI, RAG, AI agents, NLP, and intelligent workflow automation with a focus on production-ready software systems.

The role requires 5+ years in software engineering or AI, strong Python skills, and hands-on expertise with LLMs, vector databases, and cloud infrastructure. Remote work within the United States is supported.

Qualifications

• Minimum 5 years of professional experience in software engineering, ML/AI, or related field.
• Proficiency in Python and modern software engineering practices.
• Hands-on with LLMs, generative AI frameworks, or foundation model APIs.
• Understanding of transformer architectures, embeddings, and LLM inference.
• Experience building Retrieval-Augmented Generation (RAG) solutions.
• Familiarity with LangChain, LangGraph, LlamaIndex, Hugging Face Transformers.
• Experience with vector databases (Pinecone, Weaviate, Milvus, Chroma, FAISS, pgvector).
• Knowledge of prompt engineering, function calling, structured generation, and LLM evaluation methodologies.
• Experience developing REST APIs and backend services.
• Familiarity with PyTorch, TensorFlow, or similar frameworks.
• Experience with AWS, Azure, or GCP.
• Understanding of Docker, Kubernetes, CI/CD, and cloud-native deployment.
• Knowledge of AI security, data privacy, and governance principles.
• Experience with fine-tuning/LoRA/PEFT and agentic AI architectures is a plus.

Responsibilities

• Design, develop, test, deploy, and maintain enterprise-grade Generative AI applications and services.
• Build and optimize LLM-powered applications, RAG pipelines, and AI agents.
• Integrate foundation models and LLM APIs into scalable software and workflows.
• Develop AI orchestration using LangChain, LangGraph, LlamaIndex or comparable tools.
• Implement document ingestion, semantic search, embeddings, and vector retrieval.
• Create prompt templates, structured outputs, tool-calling workflows, and context-management strategies.
• Evaluate AI quality with testing, benchmarks, and human feedback.
• Address hallucinations, prompt injection and data privacy concerns.
• Develop backend services and APIs using Python, FastAPI, or equivalent.
• Support model selection, fine-tuning, and inference optimization.
• Build scalable deployment workflows on cloud, containers, and CI/CD.

Skills

Python

LLM development

Prompt engineering

Vector databases

REST APIs

Cloud platforms

CI/CD

Education

Bachelor's degree in CS or related

Tools

LangChain

LangGraph

LlamaIndex

Hugging Face Transformers

Pinecone

Weaviate

Milvus

Chroma

FAISS

pgvector

PyTorch

TensorFlow

FastAPI

Docker

Kubernetes

CI/CD

Job description

Success Recruitments is seeking an experienced Generative AI Engineer to design, develop, and deploy AI-powered applications for enterprise environments. You will work on LLMs, GenAI, RAG, AI agents, NLP, and intelligent workflow automation with a focus on production-ready software systems.

The role requires 5+ years in software engineering or AI, strong Python skills, and hands-on expertise with LLMs, vector databases, and cloud infrastructure. Remote work within the United States is supported.