AI Engineer

Scalio; Bengaluru; On-site; INR 900,000 - 1,800,000; Full time

Job summary

Scalio is seeking an engineer to build and deploy large language model systems that serve real users. You will design and implement retrieval-augmented generation pipelines, embeddings, and vector databases, plus create intelligent agents capable of tool use within AI workflows.

The role emphasizes prompt engineering, model integration, and multi-step reasoning to handle complex tasks. Applicants should have hands-on experience shipping production AI systems and 2-5 years as a software engineer.

Qualifications

• 2-5 years of experience as a software engineer with strong Python expertise.
• Proven track record shipping production AI and LLM systems to users.
• Experience implementing RAG architectures, embedding models, and vector databases.
• Hands-on work building multi-step agent systems with tool calling capabilities.
• Background constructing context management and state handling in AI workflows.

Responsibilities

• Build and deploy large language model systems that serve real users and customers.
• Develop retrieval-augmented generation pipelines, embedding workflows, and vector database implementations.
• Create intelligent agents capable of tool use and manage complex context flows within AI applications.
• Design systems that handle prompt engineering, model integration, and multi-step reasoning tasks.

Skills

Python

AI/LLM systems

RAG architectures

Vector embeddings

Multi-step agents

Tools

LangGraph

LlamaIndex

OpenAI Agents SDK

pgvector

Docker

Job description

Batch: 2020/2021/2022/2023/2024.

About the role:

• Build and deploy large language model systems that serve real users and customers
• Develop retrieval-augmented generation pipelines, embedding workflows, and vector database implementations
• Create intelligent agents capable of tool use and manage complex context flows within AI applications
• Design systems that handle prompt engineering, model integration, and multi-step reasoning tasks

What we're looking for:

• 2-5 years working as a software engineer with strong Python expertise
• Proven track record shipping production AI and LLM systems to users
• Experience implementing RAG architectures, embedding models, and vector database solutions
• Hands-on work building multi-step agent systems with tool calling capabilities
• Background constructing context management and state handling in AI workflows

Nice to have:

• Familiarity with LangGraph, LlamaIndex, or OpenAI Agents SDK
• Experience using PydanticAI or the Model Context Protocol (MCP)
• Knowledge of pgvector or similar vector database extensions
• Competence deploying systems with Docker