Artificial Intelligence Engineer

Aventra.AI; Ahmedabad District; On-site; INR 1,600,000 - 3,200,000; Full time

Job summary

Aventra.AI in Ahmedabad, India, seeks an AI Engineer with 3–6 years of hands-on experience in Python, ML, Generative AI, and LLMs to design and deploy AI-powered applications.

You will work across the full AI development lifecycle, collaborate with data scientists and engineers, implement RAG pipelines, vector databases, and deploy solutions on cloud platforms such as Azure, AWS, or GCP.

Qualifications

• 3–6 years of hands-on AI/ML experience.
• Proficient in Python and software development practices.
• Experience with NLP and deep learning concepts.
• Familiar with ML frameworks such as Scikit-learn, PyTorch, TensorFlow.
• Experience developing and deploying ML models.
• Understanding of data pipelines and model evaluation.
• Knowledge of LLMs and Generative AI concepts.
• Experience with RAG and vector databases.

Responsibilities

• Develop and deploy AI/ML and Generative AI applications using Python.
• Build LLM-powered applications with platforms like OpenAI, Azure OpenAI, Gemini.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines.
• Design document ingestion, chunking, embeddings, retrieval and response generation pipelines.
• Build AI applications using frameworks such as LangChain, LangGraph, LlamaIndex.
• Implement prompt engineering, structured outputs, function calling and tool integration.
• Develop and integrate AI agents and basic agentic workflows.
• Work with vector databases and search technologies for semantic/hybrid search.
• Develop REST APIs and integrate AI capabilities into existing apps.
• Perform model evaluation, prompt testing, performance optimization and troubleshooting.
• Collaborate with data scientists, software engineers, architects and product teams.
• Deploy and maintain AI apps on cloud platforms such as Azure, AWS or GCP.
• Follow best practices around security, responsible AI, data privacy, monitoring and scalability.

Skills

Python

Machine Learning fundamentals

Generative AI

LLMs

AI application development

RAG pipelines

vector databases

cloud platforms

AI agents & workflows

API development

Education

Bachelor's or Master's in Computer Science/AI/Data Science/Engineering

Tools

Scikit-learn

PyTorch

TensorFlow

LangChain

LangGraph

LlamaIndex

Pinecone

FAISS

Elasticsearch

Docker

Kubernetes

OpenAI

Job description

We are looking for a skilled AI Engineer with 3–6 years of hands-on experience in Python, Machine Learning, Generative AI, LLMs, and AI application development.

The ideal candidate will have experience building and integrating AI/ML solutions, developing LLM-powered applications, implementing RAG pipelines, working with vector databases, and deploying AI solutions on cloud platforms. Experience with AI agents and agentic workflows is highly desirable.

The candidate should be comfortable working across the complete AI development lifecycle—from experimentation and prototyping to deployment and production support.

Key Responsibilities

• Develop and deploy AI/ML and Generative AI applications using Python.
• Build applications using Large Language Models (LLMs) such as OpenAI, Azure OpenAI, Anthropic, Gemini, or equivalent models.
• Develop RAG-based applications for enterprise knowledge retrieval and question-answering.
• Design document ingestion, chunking, embedding, retrieval, and response-generation pipelines.
• Build AI applications using frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent frameworks.
• Implement prompt engineering, structured outputs, function calling, and tool integration.
• Develop and integrate AI agents and basic agentic workflows.
• Work with vector databases and search technologies for semantic and hybrid search.
• Develop REST APIs and integrate AI capabilities into existing applications.
• Perform model evaluation, prompt testing, performance optimization, and troubleshooting.
• Build reusable AI components and services that can be integrated into enterprise applications.
• Work with data scientists, software engineers, architects, and product teams to deliver AI solutions.
• Deploy and maintain AI applications using cloud platforms such as Microsoft Azure, AWS, or GCP.
• Follow best practices around security, responsible AI, data privacy, monitoring, and scalability.

Required Skills

Programming

• Strong hands-on experience with Python.
• Good understanding of object-oriented programming and software development practices.
• Good knowledge of Git and software development workflows.
• Strong understanding of Machine Learning fundamentals.
• Experience with supervised and unsupervised learning.
• Knowledge of NLP and deep learning concepts.
• Experience using frameworks such as Scikit-learn, PyTorch, or TensorFlow.
• Experience developing and deploying ML models.

Generative AI & LLM

• Hands-on experience with Generative AI and LLM-based applications.
• Experience with OpenAI / Azure OpenAI / Anthropic / Gemini or similar models.
• Strong understanding of:
• Prompt Engineering
• Embeddings
• Context Windows
• Function/Tool Calling
• Structured Outputs
• LLM Evaluation

RAG & Vector Databases

• Hands-on experience implementing Retrieval-Augmented Generation (RAG).
• Understanding of document processing, chunking, metadata, embeddings, and retrieval.
• Experience with one or more vector/search technologies:
• Pinecone
• FAISS
• Chroma
• Weaviate
• Milvus
• Elasticsearch / OpenSearch

AI Frameworks

Experience with one or more:

• LangChain
• LangGraph
• Semantic Kernel
• AutoGen
• CrewAI
• Experience with at least one cloud platform:
• AWS
• Google Cloud
• Basic understanding of Docker and containerized deployments.
• Understanding of CI/CD and cloud deployment practices is preferred.

Preferred Skills

• Exposure to Agentic AI and AI agents.
• Experience developing multi-step AI workflows.
• Knowledge of MCP (Model Context Protocol) is a plus.
• Experience with LLM observability and evaluation tools.
• Knowledge of MLOps / LLMOps.
• Experience working with SQL and NoSQL databases.
• Knowledge of Kubernetes is a plus.
• Experience with enterprise AI solutions is preferred.

Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related field.
• 3–6 years of relevant experience in AI/ML, Generative AI, or software engineering.
• Strong analytical and problem-solving skills.
• Good communication and collaboration skills.