AI Engineer

The Dievision; Ahmedabad District; Hybrid; INR 1,500,000 - 3,000,000; Full time

Benefits offered by this job

Remote-friendly work policy

Flexible working hours

Access to top-tier AI tooling

Job summary

The Dievision is seeking an experienced AI engineer to join our core AI engineering team in India. You will architect autonomous AI agents, build multi-step LLM workflows, and deploy RAG pipelines for enterprise clients, integrating OpenAI, Anthropic, Gemini and open-source models via APIs and tooling.

Develop backend services in Python and Node.js to support real-time AI automation and voice agents, while evaluating model performance, latency, and cost across production deployments.

Qualifications

• 2+ years of experience with Python, LLMs, LangChain, or agentic frameworks.
• Familiarity with prompt engineering and vector databases.
• Experience deploying production ML/AI endpoints with containerization and cloud services.
• Knowledge of fine-tuning, embeddings, and rate-limiting strategies.

Responsibilities

• Architect and implement autonomous AI agents, multi-step LLM workflows, and RAG pipelines.
• Integrate foundation models via APIs and custom tooling.
• Develop backend services in Python / Node.js for real-time AI automation and voice agents.
• Evaluate model accuracy, latency, guardrails, and cost in production.
• Collaborate with product and engineering teams to ship AI features in 2–4 week sprints.

Skills

Python

LLMs

LangChain

LlamaIndex

RAG workflows

prompt engineering

vector databases

Pinecone

Qdrant

Chroma

FastAPI

Docker

cloud services

embeddings

API rate-limiting

Tools

FastAPI

Docker

Job description

Join our core AI engineering team to build, fine-tune, and deploy production-ready AI agents, LLM applications, voice assistants, and intelligent workflow automations for enterprise clients.

Responsibilities

• Architect and implement autonomous AI agents, multi-step LLM workflows, and RAG pipelines
• Integrate foundation models (OpenAI, Anthropic, Gemini, open-source models) via APIs and custom tooling
• Develop backend services in Python / Node.js to support real-time AI automation and voice agents
• Evaluate model accuracy, latency, guardrails, and cost efficiency across production deployments
• Collaborate closely with product and engineering teams to ship bespoke AI features in 2-4 week sprints

Requirements

• 2+ years of experience working with Python, LLMs, LangChain, LlamaIndex, or agentic frameworks
• Strong understanding of prompt engineering, vector databases (Pinecone, Qdrant, Chroma), and RAG
• Experience deploying production ML/AI endpoints with FastAPI, Docker, and cloud services
• Familiarity with fine-tuning techniques, embeddings, and API rate-limiting strategies
• Passion for shipping pragmatic, reliable AI systems that solve real business bottlenecks
• Competitive salary with performance incentives
• Work directly on high-impact generative AI and automation products
• Flexible working hours and remote flexibility
• Access to top-tier AI tooling, GPUs, and developer resources
• Mentorship and rapid career progression in a growing agency