Junior AI Engineer

Job Description

Role Overview

We are looking for a motivated AI Engineer with hands-on experience in Python and cloud platforms (AWS/Azure) to design, build, and deploy Generative AI solutions. This is a practical engineering role focused on LLM integrations, RAG pipelines, and AI-driven applications.

Key Responsibilities

• Build and integrate applications using Large Language Models (LLMs)
• Develop RAG pipelines and prompt workflows
• Integrate AI services (OpenAI, Azure OpenAI, AWS Bedrock)
• Build chatbots, assistants, and AI automation tools

• Write scalable Python code for AI workflows
• Develop REST APIs using FastAPI/Flask
• Work with JSON, embeddings, and vector databases
• Build data pipelines for AI systems

• Deploy applications on AWS (S3, Lambda, EC2, API Gateway, Bedrock) or Azure
• Work with Azure OpenAI, Functions, Blob Storage, App Services
• Use Docker for containerization
• Support CI/CD pipelines

• Work with structured and unstructured data
• Build integrations with databases (PostgreSQL, MySQL, SQL Server)
• Implement vector search (FAISS, Pinecone, OpenSearch)
• Support model evaluation and logging

• 1–3 years in software engineering / AI development
• Strong Python coding (hands-on)
• Experience with APIs and JSON integrations
• Practical exposure to LLMs, prompt engineering, embeddings
• Understanding of RAG concepts
• Experience with AWS or Azure cloud platforms
• Familiarity with Git and collaborative workflows

• Experience with LangChain, LlamaIndex
• Exposure to Azure OpenAI or AWS Bedrock
• FastAPI experience
• Knowledge of vector databases
• Understanding of MLOps and model evaluation
• Exposure to Databricks (plus)

• Strong problem-solving mindset
• Curiosity for emerging AI technologies
• Ability to adapt in fast-paced environments
• Good communication and collaboration skills