ROLE OVERVIEW

We are looking for a hands-on Python Engineer with strong backend development and system architecture experience, along with practical exposure to Large Language Models (LLMs) and Agentic AI.

The ideal candidate should be capable of designing and developing scalable backend applications, building AI powered workflows, integrating LLM APIs, and deploying production-grade solutions on AWS.

This role requires a combination of strong software engineering fundamentals, cloud infrastructure knowledge, and an understanding of how modern AI systems and autonomous agents work.

KEY RESPONSIBILITIES

Design, develop, and maintain scalable backend applications using Python and Django.

Build REST APIs and integrate third-party services, including OpenAI and other LLM providers.

Design and implement AI-powered applications using LLMs, prompt engineering, and agentic workflows.

Develop AI agents capable of reasoning, tool calling, executing tasks, and interacting with external systems.

Work with LLM concepts such as tokens, context windows, system prompts, embeddings, and model limitations.

Design scalable system architectures, including asynchronous processing, caching, databases, and distributed components.

Deploy, manage, and optimize applications on AWS infrastructure.

Work with cloud services, infrastructure components, monitoring, security, and scalability.

Write clean, maintainable, and efficient code with appropriate testing and documentation.

Optimize LLM integrations for latency, cost, reliability, and performance.

MANDATORY SKILLS

Strong hands-on experience in Python development.

Experience building backend applications using Django.

Strong understanding of REST APIs and API integrations.

Experience with system architecture and designing scalable applications.

Hands-on AWS experience and understanding of cloud infrastructure.

Practical experience integrating LLM APIs, preferably OpenAI.

Understanding of LLM fundamentals, including tokens, context windows, system prompts, and prompt engineering.

Practical exposure to Agentic AI, AI agents, tool calling, and multi-step AI workflows.

Strong coding, debugging, and problem-solving skills.

PREFERRED SKILLS

Experience with LangChain, LangGraph, or similar AI orchestration frameworks.

Experience with RAG (Retrieval-Augmented Generation), vector databases, and embeddings.

Knowledge of Docker, Kubernetes, CI/CD, and infrastructure automation.

Experience with asynchronous processing using Celery, Redis, or message queues.

Experience building and deploying production-grade AI applications.

IDEAL CANDIDATE

A backend engineer who can independently design and build Python applications, understand cloud infrastructure, and implement end-to-end AI solutions using LLMs and Agentic AI—not someone with only theoretical AI knowledge.