RAG AI Engineer: Build Scalable, Production-Grade LLM Apps

JPC TECHNO INC; New Jersey; On-site; USD 130,000 - 180,000; Full time

Job summary

JPC TECHNO INC is seeking an AI/ML Developer with hands-on experience in Generative AI, RAG, AI agents, and prompt engineering. You will design scalable AI solutions using LLMs, vector databases, and agentic workflows in a secure context-managed environment.

You will build RAG pipelines, develop intelligent agents, craft prompts, and implement guardrails to mitigate prompt injection while integrating LLMs with enterprise systems and APIs.

Qualifications

• Hands-on Python and AI/ML development experience.
• Strong knowledge of Generative AI, LLMs and RAG architectures.
• Experience with vector embeddings and vector databases (Pinecone, FAISS, Chroma).
• Experience developing AI agents, tool calling, function calling, and API integrations.
• Familiarity with Model Context Protocol (MCP) and agentic frameworks.
• Strong understanding of context engineering, prompt design, context-window management, and prompt injection mitigation.
• Experience evaluating AI systems for latency and scalability.

Responsibilities

• Design and implement RAG pipelines with embeddings and vector DBs.
• Develop AI agents and agentic workflows using LLMs and function calls.
• Engineer prompts and manage context windows for accuracy.
• Implement guardrails to mitigate prompt injection and security risks.
• Integrate LLMs with enterprise apps and external APIs.
• Test and optimize AI solutions for quality, latency, scalability.
• Collaborate with engineering and product teams to deliver production-ready AI apps.

Skills

Python

AI/ML development

Generative AI

LLMs

RAG

vector embeddings

semantic search

MCP

prompt design

context engineering

prompt injection mitigation

LLM evaluation

Tools

Pinecone

FAISS

Chroma

LangChain

LangGraph

LlamaIndex

FastAPI

Docker

Kubernetes

Job description

JPC TECHNO INC is seeking an AI/ML Developer with hands-on experience in Generative AI, RAG, AI agents, and prompt engineering. You will design scalable AI solutions using LLMs, vector databases, and agentic workflows in a secure context-managed environment.

You will build RAG pipelines, develop intelligent agents, craft prompts, and implement guardrails to mitigate prompt injection while integrating LLMs with enterprise systems and APIs.