64703 Jr AI Engineer

Cephas Consultancy Services Private Limited; Pune District; On-site; INR 900,000 - 1,500,000; Full time

Job summary

Cephas Consultancy Services Private Limited in Pune is seeking a software professional to design, build, and deploy AI/GenAI solutions. You will work with senior engineers to create scalable, reliable systems and advance RAG, chatbots, and automation tools.

The role requires 2–4 years in software engineering or AI/ML, familiarity with APIs, microservices and cloud platforms (AWS/Azure/GCP), and a strong learning mindset.

Qualifications

• 2–4 years of experience in software engineering or AI/ML roles.
• Basic understanding of LLMs, RAG, and AI application development.
• Familiarity with APIs, microservices, and databases (SQL/NoSQL).
• Exposure to cloud platforms (AWS/Azure/GCP).
• Strong problem-solving and learning mindset.

Responsibilities

• Assist in building and deploying AI/ML and GenAI applications (RAG, chatbots, automation tools)
• Develop and maintain APIs using Python/Node.js (FastAPI, Flask, etc.)
• Work on data preprocessing, embeddings, and basic vector search implementations
• Support ingestion pipelines and data workflows
• Participate in prompt engineering, testing, and evaluation activities
• Contribute to debugging, monitoring, and performance optimization
• Collaborate with cross-functional teams on feature delivery

Skills

AI/ML experience

LLMs knowledge

APIs & microservices

Cloud platforms

Problem-solving mindset

RAG basics

Tools

LangChain

Semantic Kernel

Docker

CI/CD

Pinecone

Weaviate

Job description

About this position

Positions:2 Full Time
Experience
2 - 4 Years

Job Description

Role Summary:

Support the design, development, and deployment of AI/GenAI solutions, working closely with senior engineers to build scalable and reliable systems.

Key Responsibilities

• Assist in building and deploying AI/ML and GenAI applications (RAG, chatbots, automation tools)
• Develop and maintain APIs using Python/Node.js (FastAPI, Flask, etc.)
• Work on data preprocessing, embeddings, and basic vector search implementations
• Support ingestion pipelines and data workflows
• Participate in prompt engineering, testing, and evaluation activities
• Contribute to debugging, monitoring, and performance optimization
• Collaborate with cross-functional teams on feature delivery

Required Skills

• 2–4 years of experience in software engineering or AI/ML roles
• Basic understanding of LLMs, RAG, and AI application development
• Familiarity with APIs, microservices, and databases (SQL/NoSQL)
• Exposure to cloud platforms (AWS/Azure/GCP)
• Strong problem-solving and learning mindset

Preferred Skills

• Experience with tools like LangChain, Semantic Kernel, or similar frameworks
• Understanding of Docker and basic CI/CD practices
• Exposure to vector databases (Pinecone, Weaviate, etc.)