AI Engineer

# AI Engineer (Project-Based Contract)

**Location:** Remote
**Job Type:** Contract / Freelance
**Project Duration:** 2–3 Months (Possible Extension)

## About the Project

We are looking for a talented AI Engineer to help us build an AI-powered application using modern Large Language Model (LLM) technologies. You will work closely with our development team to design, develop, and deploy intelligent features such as Retrieval-Augmented Generation (RAG), AI agents, document processing, and workflow automation.

This is an excellent opportunity for engineers who enjoy solving real-world problems with Generative AI and building production-ready applications.

## Responsibilities

* Design and develop AI-powered applications using Python.
* Build scalable REST APIs using FastAPI.
* Implement Retrieval-Augmented Generation (RAG) pipelines.
* Integrate Large Language Models (OpenAI, Anthropic, Gemini, or similar).
* Develop document ingestion pipelines for PDF, DOCX, CSV, and other file formats.
* Generate and manage embeddings for semantic search.
* Configure and optimize vector databases such as Qdrant, Pinecone, or Chroma.
* Build AI agents and multi-agent workflows using LangChain or LangGraph.
* Optimize prompts to improve AI response quality and reduce hallucinations.
* Integrate AI services with existing web applications and third-party APIs.
* Work with PostgreSQL and Redis for application data and caching.
* Containerize applications using Docker.
* Collaborate with frontend developers and product stakeholders.
* Write clean, maintainable, and well-documented code.

## Required Qualifications

* Strong experience with Python development.
* Experience building REST APIs with FastAPI.
* Understanding of Large Language Models (LLMs) and Generative AI.
* Experience with LangChain, LangGraph, or similar AI frameworks.
* Familiarity with vector databases such as Qdrant, Pinecone, Weaviate, or Chroma.
* Experience with embedding models and semantic search.
* Knowledge of SQL databases, preferably PostgreSQL.
* Experience using Git and GitHub for version control.
* Understanding of Docker and containerized deployments.
* Strong problem-solving and debugging skills.
* Good written and verbal English communication skills.

## Preferred Qualifications

* Experience deploying AI applications to cloud platforms.
* Knowledge of Redis, Celery, or background job processing.
* Experience with React or other frontend frameworks.
* Familiarity with CI/CD pipelines.
* Experience working with enterprise AI applications.
* Knowledge of prompt engineering and evaluation techniques.
* Experience integrating external APIs and automation workflows.

## Nice-to-Have Skills

* n8n or workflow automation platforms
* Azure OpenAI or AWS Bedrock
* Hugging Face Transformers
* OCR and document intelligence
* AI chatbots and conversational AI
* Authentication and role-based access control
* Monitoring and logging tools

## What You'll Build

During this project, you'll help develop features such as:

* AI-powered document search
* Enterprise RAG system
* Intelligent chatbot with citations
* Multi-agent AI workflows
* Knowledge base management
* Semantic search
* AI workflow automation
* Admin dashboard
* Secure authentication
* Production-ready REST APIs

## What We Offer

* Fully remote work
* Flexible working hours
* Competitive project-based compensation
* Opportunity for contract extension or long-term collaboration
* Exposure to modern AI technologies and production systems
* Collaborative and supportive engineering environment

If you're passionate about Generative AI and enjoy building practical, production-ready AI applications, we'd love to hear from you. Please include your resume, portfolio, GitHub profile, and any relevant AI projects with your application.