AI Engineer

NewVision Software & Consultancy Pvt. Ltd; United States; Remote; USD 120,000 - 180,000; Part time

Job summary

NewVision Software & Consultancy Pvt. Ltd. is seeking a Software/AI Engineer for a remote 6-month contract.

The role focuses on cloud-based data and AI engineering, GenAI, LLMs, RAG architectures, and AI application development. You will build, deploy, and integrate AI-powered solutions on AWS or GCP with strong Python and modern language skills. The ideal candidate will design end-to-end AI systems, work with various LLMs, implement RAG pipelines, and ensure production-grade quality,

Qualifications

• Strong hands-on programming with production-grade code in Python, C#, Java, JS or TS.
• Hands-on cloud experience with AWS or GCP; Azure is a plus.
• Deep knowledge of Generative AI, LLMs, embeddings, retrieval, and RAG workflows.

Responsibilities

• Design, develop, and deploy cloud-based data and AI solutions on AWS or GCP.
• Build scalable, production-ready applications using Python and other languages.
• Develop and integrate Generative AI and LLM-powered applications.
• Work with OpenAI/GPT, Meta Llama, Google Gemini, and other LLMs.
• Implement Retrieval-Augmented Generation (RAG) pipelines and vector databases.
• Utilize LangChain, LlamaIndex, LangGraph, and similar GenAI frameworks.
• Develop AI agents and backend services to expose AI capabilities.
• Establish monitoring, testing, and observability for AI/LLM apps.
• Ensure performance, scalability, security, and cost optimization.
• Collaborate with architects, data engineers, and product teams to translate requirements into solutions.

Skills

Python

C# / .NET

Java

JavaScript

TypeScript

AWS / GCP

Azure

Generative AI / LLM

LangChain / LlamaIndex / LangGraph

RAG / AI applications

Embeddings / Vector search

Job description

Job Title: Software/AI Engineer

Location: Remote

Job Type: 6 months contract

Job Summary
We are looking for a strong experience in cloud-based data and AI engineering, Generative AI, Large Language Models (LLMs), RAG architectures, and AI application development.
The ideal candidate will have practical experience building and deploying AI/GenAI solutions on AWS or Google Cloud Platform, with Azure experience being a plus. The candidate should be comfortable working with LLMs, RAG architectures, AI frameworks, data pipelines, APIs, and production-grade cloud applications.
This is a hands-on engineering role requiring strong programming skills and the ability to design, develop, integrate, test, troubleshoot, and deploy AI-powered solutions.

Key Responsibilities

• Design, develop, and deploy cloud-based data and AI solutions using AWS or Google Cloud Platform.

• Build scalable and production-ready applications using Python and other modern programming languages.

• Develop and integrate Generative AI and LLM-powered applications.

• Work with commercial and open-source LLMs such as:

• OpenAI / GPT

• Meta Llama

• Google Gemini

• Other open-source LLMs

• Build and implement Retrieval-Augmented Generation (RAG) solutions.

• Design RAG pipelines including document ingestion, preprocessing, chunking, embeddings, retrieval, reranking, context management, and response generation.

• Work with LangChain, LlamaIndex, LangGraph, and similar GenAI frameworks.

• Develop AI agents and graph-based AI workflows where applicable.

• Build integrations between LLMs, enterprise applications, APIs, databases, data platforms, and cloud services.

• Develop data ingestion and transformation pipelines supporting AI/ML and GenAI applications.

• Work with both structured and unstructured data.

• Implement vector search, embeddings, and vector database solutions.

• Build APIs and backend services to expose AI capabilities to enterprise applications.

• Implement monitoring, logging, testing, evaluation, and observability for AI/LLM applications.

• Optimize AI applications for performance, scalability, reliability, security, and cost.

• Troubleshoot production issues and continuously improve AI and data engineering solutions.

• Collaborate with architects, data engineers, software engineers, product teams, and business stakeholders to translate requirements into technical solutions.

Required Skills & Experience

Programming Languages
Strong hands-on programming experience with one or more of the following:

• Python strongly preferred for AI/GenAI and data engineering

• C# / .NET

• Java

• JavaScript

• TypeScript

Candidates should be able to write production-quality code and should have strong software engineering fundamentals.

Cloud & Engineering

• Strong hands-on experience with AWS or Google Cloud Platform.
• Experience developing and deploying applications/services in a cloud environment.
• Experience with cloud-native architectures and services.
• Azure experience is a plus.
• Experience developing APIs and backend services.
• Experience with databases and distributed/cloud-based systems.
• Understanding of containers, serverless technologies, CI/CD, and DevOps practices is preferred.

Generative AI / LLM
Strong practical experience with Generative AI and Large Language Models, including one or more of:

• OpenAI / GPT models

• Meta Llama

• Google Gemini

• Open-source LLMs

• LLM APIs and model integration

• Prompt engineering

• Embeddings

• Vector search

• Model evaluation and optimization

RAG & AI Application Development
Hands-on experience building RAG-based applications, including:

• Document ingestion

• Data preprocessing and chunking

• Embeddings

• Vector databases / vector search

• Semantic retrieval

• Context construction

• Prompt orchestration

• Response generation

• RAG evaluation and optimization

Experience with:

• LangChain

• LlamaIndex

• LangGraph

• Other equivalent GenAI frameworks