AI Engineer (AI + Software)

Mployee.me; Delhi; On-site; INR 1,500,000 - 3,500,000; Full time

Job summary

Mployee.me in Delhi is seeking AI Engineers to build and deploy LLM-powered features in production, at the intersection of AI and Automotive. You will work with retrieval systems, ranking models, and personalization engines, designing safe, scalable AI services integrated with modern software products.

You are someone who thrives in an early-stage environment, loves fast learning, and takes ownership from day one.

Qualifications

• Proficient in Python and JavaScript
• Hands-on experience with LLMs, RAG, or applied ML in production
• Ability to thrive in an early-stage environment

Responsibilities

• Build and deploy LLM-powered features in production.
• Work with retrieval systems, ranking models, and personalization engines.
• Design safe, scalable AI services integrated with modern software products.

Skills

Python

JavaScript

LLMs

RAG

ML in production

Tools

LangGraph

LangChain

LlamaIndex

Pinecone

FAISS

Weaviate

Postgres FTS

Reciprocal Rank Fusion

LiveKit

Pipecat

Job description

Location: Mohan Estate, Delhi

Type: Full-Time

We’re building something exciting at the intersection of AI and Automotive — reimagining how intelligent software can shape the future of this industry.

We’re looking for AI Engineers who can:

• Build and deploy LLM-powered features in production.
• Work with retrieval systems, ranking models, and personalization engines.
• Design safe, scalable AI services integrated with modern software products.

You are someone who:

• Strong in Python/JS software engineering.
• Hands-on with LLMs, RAG, or applied ML in production.
• Curious, fast learner, thrives in an early-stage environment.

Tech stack you’ll work with:

• AI Agents, tool calling, and agentic workflows
• LiteLLM (LLM gateway — routing, aliases, fallbacks)
• Cloud LLMs (GPT, Claude, Gemini)
• Open-source models (Qwen, Llama, Mistral, DeepSeek)
• LangGraph, LangChain, LlamaIndex
• Embeddings (OpenAI, Voyage AI, Cohere)
• Retrieval & Vector Databases (Pinecone, Weaviate, FAISS, pgvector)
• Hybrid Retrieval (Postgres FTS + pgvector + Reciprocal Rank Fusion + rerankers)
• Speech-to-Text (STT) and Text-to-Speech (TTS) — batch & real-time streaming
• Voice AI platforms (LiveKit Agents, Pipecat)
• Multimodal document understanding and structured extraction
• FastAPI, Express, Node.js, Python
• Docker, Kubernetes, AWS/GCP
• Data pipelines and feature stores

Why join:

• Be part of a ambitious team.
• High ownership and impact from day one.
• Opportunity to build cutting-edge AI s