Senior AI Engineer: Local LLM & RAG Architect

Cyberei Technologies Pvt. Ltd.; United States; Hybrid; USD 140,000 - 230,000; Full time

Job summary

Cyberei Technologies Pvt. Ltd. is seeking a Senior AI Engineer - LLM, RAG Local AI Systems to build enterprise-grade AI applications using open-source models.

You will design and deploy scalable RAG pipelines, document ingestion workflows, and productionize local inference with a focus on privacy and ownership. The role requires 5+ years of experience and a strong background in LLMs, RAG, and local AI architectures.

Qualifications

• Extensive experience with open-source LLMs and local AI deployment.
• Proven ability to design and deploy RAG pipelines.
• Experience with vector databases and embedding models.
• Experience with production-grade inference and optimization.
• Familiarity with multi-model serving and self-hosted infra.

Responsibilities

• Design, build, and deploy enterprise-grade AI applications using open-source LLMs.
• Build scalable Retrieval-Augmented Generation (RAG) pipelines from scratch.
• Design document ingestion pipelines supporting PDFs, Office documents, websites, databases, APIs, images, and structured enterprise data.
• Implement semantic search using embedding models and vector databases.
• Deploy and optimize local AI models for production environments.
• Evaluate, benchmark, fine-tune, and optimize open-source LLMs.
• Build AI agent workflows using modern orchestration frameworks.
• Develop production-ready inference APIs.
• Optimize GPU and CPU inference performance.
• Work with quantized models (GGUF, AWQ, GPTQ, FP16, INT4, INT8).
• Build AI-powered search, recommendation, summarization, translation, OCR, and conversational systems.
• Integrate AI models with existing enterprise applications.
• Continuously evaluate emerging open-source AI models and recommend the best fit for production use.

Skills

Open-source LLMs

Prompt engineering

Model evaluation

Hallucination mitigation

Reasoning models

Tools

Ollama

vLLM

LM Studio

llama.cpp

Transformers

Text Generation Inference

CUDA

ROCm

GPU optimization

Multi-model serving

Self-hosted infra

Job description

Cyberei Technologies Pvt. Ltd. is seeking a Senior AI Engineer - LLM, RAG Local AI Systems to build enterprise-grade AI applications using open-source models.

You will design and deploy scalable RAG pipelines, document ingestion workflows, and productionize local inference with a focus on privacy and ownership. The role requires 5+ years of experience and a strong background in LLMs, RAG, and local AI architectures.