Generative AI Engineer

Overview

We are seeking a motivated Generative AI Engineer with 1–3 years of experience in Machine Learning, Generative AI, and Large Language Models (LLMs). The ideal candidate should have strong programming skills in Python, a solid understanding of ML/AI fundamentals, and hands-on experience building GenAI applications using LLMs, Retrieval-Augmented Generation (RAG), and AI agent frameworks.

The candidate will work closely with senior engineers, data scientists, and cross-functional teams to design, develop, test, and deploy scalable GenAI solutions for real-world business problems. This role offers an opportunity to work on emerging technologies, including Agentic AI, multi-agent systems, LangGraph, and open-source LLMs.

Duties and Responsibilities

• Develop and implement Generative AI applications using LLMs and modern AI frameworks.
• Build and maintain RAG pipelines using document processing, embeddings, vector databases, and semantic search.
• Implement AI agents and workflow orchestration using frameworks such as LangChain and LangGraph.
• Work with LLM APIs, including OpenAI APIs and cloud-based AI services.
• Explore and integrate open-source models such as Llama, Mistral, and other Hugging Face models.
• Perform prompt engineering and optimize prompts to improve response quality, accuracy, and consistency.
• Assist in fine-tuning, evaluating, and optimizing LLMs for specific business use cases.
• Develop Python scripts and APIs to integrate GenAI solutions with existing applications and enterprise systems.
• Implement basic evaluation frameworks to assess LLM responses, RAG retrieval quality, relevance, and hallucination.
• Optimize application performance by reducing response latency, token consumption, and computational costs.
• Deploy and support GenAI applications on cloud platforms such as Microsoft Azure or AWS.
• Follow software development best practices, including version control, testing, debugging, and code documentation.
• Collaborate with senior engineers and business teams to understand requirements and translate them into AI-powered solutions.
• Stay updated with advancements in Generative AI, LLMs, Agentic AI, and emerging AI frameworks.

Requirements

• B.Tech/M.Tech in Computer Science, Information Technology, Artificial Intelligence, or a related field.
• 1–3 years of hands-on experience in Machine Learning, AI, Data Science, or Generative AI development.
• Strong programming skills in Python and familiarity with libraries such as Pandas, NumPy, and Scikit-learn.
• Basic to intermediate understanding of Machine Learning, Deep Learning, NLP, and neural network architectures.
• Hands-on experience with LLMs, Generative AI applications, and prompt engineering.
• Practical knowledge of RAG architecture, embeddings, semantic search, and vector databases.
• Familiarity with frameworks such as LangChain, LangGraph, or Hugging Face Transformers.
• Experience integrating LLMs through OpenAI APIs or other commercial/open-source model APIs.
• Familiarity with vector databases or search technologies such as FAISS, Chroma, Pinecone, or Azure AI Search.
• Basic understanding of REST APIs, FastAPI or Flask, and application integration.
• Familiarity with Git, Docker, and software development practices is preferred.
• Exposure to cloud platforms such as Microsoft Azure or AWS is an advantage.
• Strong problem-solving skills, willingness to learn, and the ability to work collaboratively in a team.

Good to Have

• Exposure to Agentic AI workflows, tool calling, and multi-agent systems.
• Basic hands-on experience with LangGraph for stateful AI workflows.
• Familiarity with open-source LLMs such as Llama, Mistral, and similar models.
• Understanding of LLM evaluation, guardrails, hallucination mitigation, and responsible AI practices.
• Exposure to model fine-tuning, quantization, or inference optimization.
• Familiarity with MLflow or other tools for experiment tracking and model management.

Key Skills

Core: Python, Machine Learning, Generative AI, LLMs, NLP

GenAI: RAG, Prompt Engineering, Embeddings, Vector Databases, LLM Evaluation

Frameworks: LangChain, LangGraph, Hugging Face, OpenAI APIs

Deployment: FastAPI, REST APIs, Git, Docker, Azure/AWS

What We Are Looking For

A proactive and curious engineer who enjoys solving real-world problems using Generative AI, can build practical AI applications, and is eager to grow their expertise in Agentic AI, multi-agent orchestration, and scalable enterprise AI solutions.