AI Engineer (Backend) - Python

Overview

: 3.00 + years

Salary: Confidential (based on experience)

Shift: (GMT+05:30) Asia/Kolkata (IST)

Opportunity Type: Remote

Placement Type: Full time Permanent Position

(*Note: This is a requirement for one of Uplers' client - Xpergia)

What do you need for this opportunity?

Must have skills required:

AI Engineer, Python, FastAPI, AWS Bedrock, Azure AI Foundry, MCP

Xpergia is Looking for:

About The Job

We are building the next generation of AI-powered applications that deliver actionable financial and marketing insights to our clients. As an AI Engineer focused on backend development, you'll be instrumental in designing and developing multiple agentic AI applications that integrate with data lakehouses and business intelligence platforms. This is not a single-project role. You'll work on a pipeline of AI-driven solutions across various use cases, all built on a common architecture leveraging cutting-edge LLM technologies, agentic frameworks, and cloud infrastructure.

What You'll Build

• Agentic chatbot applications Agentic chatbot applications with conversational UI for financial and marketing insights
• RAG-based systems RAG-based systems that intelligently retrieve and synthesize information from enterprise data sources
• MCP (Model Context Protocol) integrations MCP (Model Context Protocol) integrations for tool calling and external system interactions
• Real-time visualization generation Real-time visualization generation including graphs, charts, and dynamic dashboards
• Sandboxed code execution environments Sandboxed code execution environments for safe AI-generated code runs
• LLM benchmarking systems LLM benchmarking systems to evaluate and switch between models (AWS Bedrock, Azure AI Foundry) as new versions emerge
• Data integration pipelines Data integration pipelines connecting to SQL-based data lakehouses and Tableau dashboards
  
  
  

Key Responsibilities

Development

• Design and develop Python backend services using FastAPI FastAPI for AI-powered applications
• Implement agentic workflows using LangChain LangChain and/or Azure AI agentic frameworks like AutoGen Azure AI agentic frameworks like AutoGen
• Build and maintain RAG systems for context-aware AI responses
• Develop MCP servers and integrations for tool calling and external API interactions
• Create sandboxed execution environments for AI-generated code and visualizations
  
  
  

Data & SQL

• Write efficient SQL queries against data lakehouses to retrieve business insights
• Integrate with Tableau dashboards and other BI platforms
• Optimize data retrieval patterns for LLM context windows
  
  
  

AI/ML Operations

• Build benchmarking systems to evaluate LLM performance across different models and providers Implement model switching logic to automatically use the most efficient/effective LLM
• Monitor and optimize token usage, costs, and response latency
• Work with AWS Bedrock and Azure AI Foundry for model deployment
  
  
  

DevOps & Deployment

• Containerize applications using Docker
• Deploy and manage services in Kubernetes (K8s) clusters
• Build and maintain GitLab CI/CD pipelines for automated testing and deployment
• Ensure scalability, reliability, and security of production systems
  
  
  

Collaboration

• Work directly with US-based clients to understand requirements and deliver solutions
• Collaborate with frontend developers (React), data engineers, and architects
• Participate in technical design discussions and architectural decisions
• Document code, APIs, and system architecture clearly
  
  
  

Technical Skills

• 3+ years of professional Python development experience
• Strong SQL skills with experience querying databases or data lakehouses
• Experience with FastAPI or similar Python web frameworks (Flask, Django)
• Hands-on experience with AWS Bedrock or Azure AI services
• Familiarity with Docker containerization
• Experience with Kubernetes (K8s) deployments
• Proficiency with Git and GitLab CI/CD or similar CI/CD tools
• Understanding of RESTful API design and development
  
  
  

AI/ML Experience

• Working knowledge of LLM technologies (GPT, Claude, Llama, etc.)
• Experience with prompt engineering and LLM application development
• Familiarity with LangChain, AutoGen, Azure AI frameworks, or similar agentic/orchestration frameworks Understanding of RAG (Retrieval-Augmented Generation) patterns
  
  
  

Soft Skills

• Excellent English communication skills (written and verbal) for US client interaction
• Ability to work autonomously and complete tasks with minimal supervision
• Strong problem-solving skills and attention to detail
• Self-motivated with ability to manage priorities and deadlines
  
  
  

• Experience with React or frontend development (bonus, not required)
• Familiarity with Tableau or other BI platforms
• Experience with data lakehouses (Databricks, Snowflake, etc.)
• Knowledge of Model Context Protocol (MCP) or similar tool-calling frameworks
• Experience building benchmarking or evaluation systems for ML models
• Background in financial services or marketing analytics
• Contributions to open-source AI/ML projects
  
  
  

• Step 1: Click On Apply! And Register or Login on our portal.
• Step 2: Complete the Screening Form & Upload updated Resume
• Step 3: Increase your chances to get shortlisted & meet the client for the Interview!
  
  
  

Our goal is to make hiring reliable, simple, and fast. Our role will be to help all our talents find and apply for relevant contractual onsite opportunities and progress in their career. We will support any grievances or challenges you may face during the engagement.

(Note: There are many more opportunities apart from this on the portal. Depending on the assessments you clear, you can apply for them as well).

So, if you are ready for a new challenge, a great work environment, and an opportunity to take your career to the next level, don't hesitate to apply today. We are waiting for you!