Python Developer- RAG & LLM

Ascendion Engineering; Hyderabad; Hybrid; INR 2,800,000 - 4,000,000; Full time

Job summary

Ascendion Engineering in Hyderabad is seeking a hands-on AI/backend engineer to design and optimize RAG workflows, LLM applications, and cloud-native microservices. You will work with Python, async programming, and modern tooling.

The role emphasizes practical implementation with LangChain, vector databases, AWS, Docker, and MCP Servers, in a hybrid setup with two onsite days per week.

Qualifications

• 6-8+ years of Python development experience
• Strong hands-on experience with RAG and LLM workflows
• Experience with LangChain and Vector Databases
• Advanced Python, preferably Python 3.11, including asynchronous programming
• Good experience with AWS
• Experience with Docker and containerized environments
• Understanding of MCP Servers

Responsibilities

• Hands-on engineering role focusing on building and optimizing AI solutions
• Work on RAG workflows, LLM applications, LangChain, and vector databases
• Collaborate to design and implement AWS-based microservices

Skills

Python

RAG workflows

LLM workflows

Asynchronous programming

Tools

LangChain

Vector Databases

AWS

Docker

MCP Servers

Job description

Role & responsibilities

This is a hands-on engineering role where you'll be working on RAG workflows, LLM applications, LangChain, vector databases and AWS-based microservices. Were particularly looking for someone who is strong in Python and has practical experience building and optimizing AI solutions, rather than just having exposure to the terminology.

• 6-8+ years of Python development experience
• Strong hands-on experience with RAG and LLM workflows
• Experience with LangChain and Vector Databases
• Advanced Python, preferably Python 3.11, including asynchronous programming
• Good experience with AWS
• Experience with Docker and containerized environments
• Understanding of MCP Servers

Location:Hyderabad
Work Model:Hybrid - 2 days onsite per week