AI Engineer

EngiNeo Solutions; Gurugram District; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

EngiNeo Solutions in Gurugram (India) is seeking a skilled AI Engineer with hands-on experience in LLMs, conversational AI, and voice AI systems to build and deploy scalable AI applications and real-time conversational platforms.

You will design RAG pipelines, embeddings, and vector database integrations, develop backend AI services with Python (FastAPI/Flask), and collaborate with product and engineering teams to productionize AI solutions.

Qualifications

• Proven experience with Python and AI backend development.
• Hands-on experience with LLMs, RAG pipelines, embeddings, and vector databases.
• Experience with LangChain, OpenAI APIs, or similar AI frameworks.
• Knowledge of FastAPI/Flask and REST APIs.
• Experience with Voice AI systems (STT/TTS) and conversational AI applications.
• Understanding of WebSockets, streaming APIs, and real-time systems.
• Familiarity with cloud platforms like AWS/GCP/Azure.
• Good understanding of prompt engineering and AI optimization techniques.

Responsibilities

• Design, develop, and deploy LLM-based AI applications and conversational AI systems.
• Build and optimize RAG pipelines, embeddings, and vector database integrations.
• Develop backend AI services using Python frameworks like FastAPI or Flask.
• Work on Voice AI applications, including STT/TTS and real-time conversational systems.
• Implement real-time communication using WebSockets or streaming APIs.
• Optimize AI application latency, context handling, and response quality.
• Integrate AI models with scalable backend architectures and cloud platforms.
• Monitor, evaluate, and improve AI system performance and output accuracy.
• Collaborate with product and engineering teams for deployment and production support.
• Work on prompt engineering, workflow optimization, and AI system enhancements.

Skills

Python

LLMs

RAG pipelines

Embeddings

Vector databases

LangChain

OpenAI APIs

REST APIs

WebSockets

Cloud platforms

Prompt engineering

Tools

FastAPI

Flask

Docker

CI/CD

Pinecone

FAISS

ChromaDB

Whisper

Job description

We are looking for a skilled AI Engineer with hands-on experience in LLMs, conversational AI, and voice AI systems. The candidate will be responsible for building and deploying scalable AI applications, RAG pipelines, and real-time conversational systems using modern AI frameworks and backend technologies.

Responsibilities:

• Design, develop, and deploy LLM-based AI applications and conversational AI systems.
• Build and optimize RAG pipelines, embeddings, and vector database integrations.
• Develop backend AI services using Python frameworks like FastAPI or Flask.
• Work on Voice AI applications, including STT/TTS and real-time conversational systems.
• Implement real-time communication using WebSockets or streaming APIs.
• Optimize AI application latency, context handling, and response quality.
• Integrate AI models with scalable backend architectures and cloud platforms.
• Monitor, evaluate, and improve AI system performance and output accuracy.
• Collaborate with product and engineering teams for deployment and production support.
• Work on prompt engineering, workflow optimization, and AI system enhancements.

Requirements:

• Strong experience with Python and AI backend development.
• Hands-on experience with LLMs, RAG pipelines, embeddings, and vector databases.
• Experience with LangChain, OpenAI APIs, or similar AI frameworks.
• Knowledge of FastAPI/Flask and REST APIs.
• Experience with Voice AI systems (STT/TTS) and conversational AI applications.
• Understanding of WebSockets, streaming APIs, and real-time systems.
• Familiarity with cloud platforms like AWS/GCP/Azure.
• Good understanding of prompt engineering and AI optimization techniques.

Preferred Skills:

• Experience with Whisper, LangGraph, Pinecone, FAISS, ChromaDB, or similar tools.
• Knowledge of Docker, CI/CD pipelines, and scalable microservices architecture.
• Experience with monitoring and evaluation frameworks for AI outputs.