Python Developer

Bristlecone; Hyderabad; Hybrid; INR 1,400,000 - 2,000,000; Full time

Job summary

Bristlecone is seeking a Python developer (6-8 years) to build, integrate, and optimize RAG workflows using LangChain and vector databases. You will manage cloud-based microservices with AWS (Lambda and ECS), containerized environments with Docker, and API backends using FastAPI and Uvicorn.

The role emphasizes building scalable, observable LLM workflows, powering data-driven applications with Qdrant, and contributing to high-availability backend systems in a hybrid Hyderabad setting.

Qualifications

• Experience with Python (3.11+ / async) and building RAG workflows.
• Strong background in LangChain and vector databases for high-accuracy data retrieval.
• Experience deploying scalable microservices on AWS (Lambda/ECS) and containerized environments.

Responsibilities

• Design and deploy LLM-driven RAG workflows using LangChain and vector databases.
• Integrate and manage vector databases like Qdrant for fast searches and retrieval.
• Develop APIs with FastAPI/Uvicorn to support high-traffic workloads.
• Implement observability with Datadog/ddtrace and robust logging.

Skills

Python

RAG workflows

LangChain

LLMs

Asynchronous programming

AWS

MCP Servers

Vector databases

APIs

Tools

Docker

FastAPI

Uvicorn

AWS Lambda

AWS ECS

Qdrant

Datadog

ddtrace

Job description

We are looking for a python developer with minimum 6-8 years specializing in Retrieval-Augmented Generation (RAG) systems, with experience in large language models (LLMs), vector databases, and cloud-based microservices. Your role will focus on building, integrating, and optimizing LLM workflows using LangChain and managing complex infrastructure with AWS services like Lambda and ECS. You'll bring expertise in containerized environments, using Docker, and work with vector databases to power data-driven applications.

You'll have opportunity to:

• RAG Workflow Development: Design and deploy LLM-driven RAG workflows using LangChain and vector databases to provide high-accuracy data retrieval and enhanced content generation.
• Vector Database Management: Integrate and manage vector databases like Qdrant for optimized, high-speed vector searches and data retrieval.
• Cloud Computing: Use AWS services, including Lambda and ECS, to build serverless architectures and scalable containerized applications.
• API & Backend Development: Build APIs with FastAPI and Uvicorn to support low-latency interactions and handle high traffic volumes.
• Monitoring & Observability: Implement observability best practices using Datadog, ddtrace, and logging tools to maintain performance and troubleshoot complex workflows.

Required Skills:

• Proficiency in LLM and RAG Workflows: experience with LangChain and vector databases, applying RAG techniques for intelligent data retrieval and generation.
• Python Proficiency (>=3.11, <3.12): Advanced Python skills, including experience with asynchronous programming.
• Proficient in AWS environment
• Understanding of MCP Servers

Location Requirement

This role is based in Hyderabad and follows a hybrid work model (2 days onsite per week).