GenAI Developer (Knowledge Graphs, LLMs, and ML Pipelines)

Muffins; India; On-site; INR 1,200,000 - 2,000,000; Full time

Benefits offered by this job

Opportunity to work with cutting-edge technologies

Make a significant impact in a startup

Part of an innovative team

Job summary

Muffins is seeking a GenAI Developer to enhance expertise in knowledge graphs and LLMs in India. You'll design knowledge graphs using Neo4j, fine-tune models, and build REST APIs. Ideal candidates have 4+ years in AI/ML development and a strong grasp of prompt engineering and machine learning pipelines. If you thrive in a fast-paced startup environment and love tackling complex challenges, we want to hear from you!

This role offers the chance to work with cutting-edge technologies and make a significant impact in a dynamic team.

Qualifications

• 4+ years of experience in AI/ML development with knowledge graphs and GenAI technologies.
• Proficient in Python and experience with Neo4j.
• Strong background in building REST APIs using Flask/FastAPI.

Responsibilities

• Design and implement knowledge graphs.
• Fine-tune open-source LLMs for specific use cases.
• Develop and maintain REST APIs.

Skills

Python

Knowledge Graphs

Fine-tuning LLMs

REST API Development

Machine Learning Pipelines

Prompt Engineering

Retrieval-Augmented Generation (RAG)

Langchain

Vision-Language Models

Tools

Neo4j

Flask

FastAPI

AWS

Job description

GenAI Developer (Knowledge Graphs, LLMs, and ML Pipelines)

Location: India

Job type: Full time

Experience required: 4 to 8 Years

Job purpose

We are seeking an experienced GenAI Developer with expertise in building knowledge graphs and fine‑tuning open‑source LLM models. The ideal candidate should have hands‑on experience in prompt engineering, retrieval‑augmented generation (RAG), multi‑agent frameworks, Langchain, and vision‑language models. The candidate should also have strong Python skills, a deep understanding of REST API development with Flask/FastAPI, and experience building end‑to‑end ML pipelines. If you’re someone with a startup mentality and a passion for solving complex problems, we’d love to hear from you!

Key responsibilities

• Design and implement knowledge graphs, preferably using Neo4j.
• Fine‑tune open‑source LLMs, such as GPT‑based or other transformer models, to optimize for specific use cases.
• Develop and implement prompt engineering strategies for optimal model performance.
• Work on Retrieval‑Augmented Generation (RAG) and multi‑agent frameworks.
• Build and deploy vision‑language models for various use cases.
• Develop and maintain REST APIs using Flask/FastAPI.
• Take full ownership of end‑to‑end machine learning pipelines, from data preprocessing to deployment and monitoring.
• Collaborate with cross‑functional teams to understand business requirements and transform them into technical solutions.
• Solve complex technical problems with a solution‑oriented mindset.
• Work autonomously in a fast‑paced, startup environment.

Skills & Qualifications

• Experience: 4+ years of experience in AI/ML development, specifically with knowledge graphs and GenAI technologies.
• Technical Expertise:
  • Proficient in Python.
  • Hands‑on experience with building knowledge graphs, preferably using Neo4j.
  • Expertise in fine‑tuning open‑source LLM models and implementing advanced AI techniques like prompt engineering, RAG, Langchain, and multi‑agent frameworks.
  • Strong experience in building REST APIs using Flask/FastAPI.
  • Experience in building end‑to‑end ML pipelines and deploying them in real‑world environments.
  • Knowledge of vision‑language models and their application.
• Problem Solving: Strong analytical and problem‑solving skills with a solution‑oriented approach.
• Work Style: Startup mentality, ability to work independently and take ownership of tasks.
• Good to Have:
  • Knowledge of cloud technologies, preferably AWS.

Why Join Us?

• Be part of an innovative and fast‑growing team.
• Work with cutting‑edge technologies and solve complex AI problems.
• Have the opportunity to make a significant impact in a dynamic startup environment.