Artificial Intelligence Engineer

Laurus Labs Ltd.; Hyderabad; On-site; INR 900,000 - 1,200,000; Full time

Job summary

Laurus Labs Ltd. is seeking an AI/ML engineer to develop AI-powered applications in Python and popular AI frameworks. You will integrate LLMs for document analysis, Q&A, and automation, and build RAG-based chatbots and knowledge assistants.

You will work with LangChain, LlamaIndex, and Hugging Face Transformers to create robust backend services and REST APIs. You will handle embeddings, semantic search, and vector databases, refine prompt engineering, and develop AI agents and automated

Qualifications

• Strong programming skills in Python.
• Hands-on experience with LLMs, NLP and Generative AI applications.
• Experience with at least one AI framework, such as LangChain, LangGraph, LlamaIndex, or Hugging Face Transformers.
• Knowledge of RAG, prompt engineering, embeddings, and semantic search.
• Experience developing REST APIs using FastAPI, Flask, or Django.
• Understanding of SQL/NoSQL databases and data integration.
• Familiarity with Git and software development practices.
• Understanding deployment in cloud and on-premise environments.

Responsibilities

• Develop AI-powered applications in Python and modern AI frameworks.
• Integrate LLMs into apps for document analysis, Q&A, summarization, and automation.
• Build and maintain RAG-based apps, chatbots, and knowledge assistants.
• Work with LangChain, LangGraph, LlamaIndex, or Transformers.
• Develop backend REST APIs with FastAPI, Flask, or Django.
• Handle embeddings, semantic search, and vector databases for info retrieval.
• Design prompt engineering methods and improve LLM reliability.
• Create AI agents and automated workflows when needed.
• Integrate AI apps with databases and enterprise systems.
• Test, troubleshoot, and optimize for performance and reliability.
• Deploy and maintain apps in cloud and on-premise environments (mandate).
• Knowledge in Git, Docker, and CI/CD for dev and deployment.
• Maintain docs and follow secure coding practices.

Skills

Python

LLMs

AI frameworks

RAG

Embeddings

REST APIs

SQL/NoSQL

Git

Cloud deployment

Tools

LangChain

LangGraph

LlamaIndex

Hugging Face Transformers

FastAPI

Flask

Django

FAISS

Pinecone

ChromaDB

Qdrant

Job description

Role & responsibilities

1. Develop AI-powered applications using Python and modern AI frameworks.
2. Integrate LLMs into applications for tasks such as document analysis, question answering, summarization, and automation.
3. Build and maintain RAG-based applications, chatbots, and knowledge assistants.
4. Work with frameworks such as LangChain, LangGraph, LlamaIndex, or Hugging Face Transformers.
5. Develop backend services and REST APIs using FastAPI, Flask, or Django.
6. Work with embeddings, semantic search, and vector databases to retrieve relevant information.
7. Develop prompt engineering techniques and improve the accuracy and reliability of LLM responses.
8. Build AI agents and automated workflows where required.
9. Integrate AI applications with databases and existing enterprise systems.
10. Test, troubleshoot, and optimize AI applications for performance, response quality, and reliability.
11. Deploy and maintain applications in cloud and on-premise environments (mandate).
12. Knowledge in Git, Docker, and CI/CD tools for application development and deployment.
13. Maintain technical documentation and follow secure coding and software development practices.

Required Skills

1. Strong programming skills in Python.
2. Hands-on experience with Large Language Models (LLMs),NLP and Generative AI applications.
3. Experience with at least one AI framework, such as LangChain, LangGraph, LlamaIndex, or Hugging Face Transformers.
4. Knowledge of RAG, prompt engineering, embeddings, and semantic search.
5. Experience developing REST APIs using FastAPI, Flask, or Django.
6. Understanding of SQL/NoSQL databases and data integration.
7. Familiarity with Git and software development practices.
8. Understanding of application deployment in cloud and on-premise environments.

Preferred candidate profile

1. Experience with vector databases such as FAISS, Pinecone, ChromaDB, or Qdrant.
2. Knowledge of AI agents, multi-agent workflows, and tool/function calling.
3. Experience with LLM evaluation, response validation, and hallucination reduction.
4. Familiarity with Docker, CI/CD, and application monitoring.
5. Exposure to LLM fine-tuning techniques such as LoRA or QLoRA.
6. Experience integrating AI solutions with enterprise applications and business workflows.
7. Experience in pharmaceutical, life sciences, healthcare, or other regulated industries is an added advantage.