Junior Software Engineer (AI)

Dash Technologies Inc; Ahmedabad District; On-site; INR 800,000 - 1,200,000; Full time

Job summary

Dash Technologies Inc is seeking a Junior AI Engineer — GenAI Application Development with 2-3 years of software experience. You’ll build GenAI components in Python, create FastAPI REST APIs, and integrate with OpenAI/Azure OpenAI.

Part of a team with Senior AI Engineers and AI Architects, you’ll work on RAG pipelines, embeddings, and testing in a containerized environment. You will deepen expertise in LLMs, GenAI frameworks, and modern AI app development, contributing to end-to-end GenAI

Qualifications

• 2–3 years of software development experience.
• Strong foundation in Python and backend development.
• Familiar with building AI-enabled applications and APIs.

Responsibilities

• Develop and maintain GenAI application components using Python.
• Build REST APIs with FastAPI.
• Integrate with LLM APIs such as OpenAI and Azure OpenAI.
• Implement basic RAG pipelines for enterprise apps.
• Work with document processing, embeddings, and retrieval.
• Write unit and integration tests for AI and backend components.
• Containerize applications using Docker and manage deployments.
• Collaborate with Senior Engineers and Architects on designs.

Skills

Python

FastAPI

SQL

Backend development

APIs

Git

Docker

Unit tests

OpenAI APIs

Azure OpenAI

Tools

PostgreSQL

LangChain

Redis

OpenAI APIs

Job description

We are looking for a Junior AI Engineer — GenAI Application Development with 2–3 years of software development experience and an interest in building practical Generative AI applications.

The candidate will work closely with Senior AI Engineers and AI Architects to develop and maintain GenAI application components, APIs, RAG pipelines, integrations, and automated tests.

This role is ideal for a software engineer who has a strong foundation in Python and backend development and is looking to build deeper expertise in LLMs, RAG, AI Agents, and modern AI application development.

Key Responsibilities

• Develop and maintain GenAI application components using Python.
• Build REST APIs using FastAPI.
• Integrate applications with LLM APIs such as OpenAI and Azure OpenAI.
• Implement basic RAG pipelines for enterprise applications.
• Work with document processing, chunking, embeddings, and retrieval.
• Integrate applications with databases and external services.
• Write SQL queries and work with relational databases.
• Develop reusable and maintainable Python code.
• Write unit tests and integration tests for AI and backend components.
• Debug and resolve application, API, database, and LLM integration issues.
• Use Git for source-code management and collaborative development.
• Containerize applications using basic Docker practices.
• Support deployment and troubleshooting in development and test environments.
• Work with Senior Engineers to implement technical designs and AI workflows.
• Participate in code reviews, technical discussions, and documentation.
• Learn and adopt new GenAI frameworks and technologies as required.

Must-Have Skills

• Good hands-on knowledge of Python
• FastAPI
• SQL
• Understanding of backend application development
• Basic knowledge of API integration and error handling

Generative AI

• Basic understanding of Generative AI and LLMs
• Experience integrating LLM APIs
• Understanding of:
  • Prompts and prompt templates
  • Tokens and context
  • LLM parameters
  • Structured responses
  • Basic hallucination concepts

RAG

• Basic hands-on experience with Retrieval-Augmented Generation (RAG)
• Understanding of:
  • Document ingestion
  • Text chunking
  • Embeddings
  • Vector search
  • Context retrieval
  • Prompt/context construction

Development Tools

• Basic Docker
• Debugging and troubleshooting
• Basic software testing practices

Preferred Skills

Exposure to any of the following will be an advantage:

• LangChain
• LangGraph
• OpenAI APIs
• Open-source LLMs
• React / Next.js
• Redis
• CI/CD

Technical Expectations

The candidate should be able to perform tasks such as:

• Integrate an LLM API into a Python application.
• Create a basic RAG workflow.
• Generate and use embeddings for document retrieval.
• Connect an application to PostgreSQL or another database.
• Create basic prompt templates.
• Implement basic validation and error handling for LLM responses.
• Write unit tests for APIs and application components.
• Create a Dockerfile and run a Python application in Docker.
• Use Git effectively for branching, commits, pull requests, and code reviews.
• Debug API, database, and LLM integration issues.

This role provides an opportunity to grow from GenAI application development toward advanced AI engineering.

The candidate is expected to progressively develop skills in:

• Advanced RAG
• Agentic AI
• LangGraph
• LLM evaluationAI guardrails
• Vector and graph databases
• MCP
• Open-source LLMs
• Cloud-based AI deployment

What We Are Looking For

• Genuine interest in Generative AI and LLM technologies.
• Ability to understand and implement technical requirements.
• Good debugging and problem-solving skills.
• Willingness to learn new AI frameworks and technologies.
• Ability to work effectively with Senior Engineers and Architects.
• Good communication and teamwork.
• Attention to code quality, testing, and documentation.