GenAI Developer - Fullstack/Backend Python

What Were Looking For

• 8-14 years of experience in software engineering (backend or fullstack)
• 2+ years of hands-on experience with LLMs (RAG, agents, prompt engineering)
• Strong experience building production-grade distributed systems
• Proficiency in Python
• Strong experience with SQL & NoSQL databases
• Hands-on experience with LangChain, LangGraph, or similar frameworks
• Experience deploying systems on AWS / Azure / GCP
• Strong understanding of APIs, microservices, and system design
• Experience with vector databases (Pinecone, Weaviate, FAISS, etc.)
• Familiarity with CI/CD pipelines and DevOps practices

Roles & Responsibilities

• Develop and optimize LLM-based solutions: Lead the design and deployment of large language models, leveraging techniques like prompt engineering, retrieval-augmented generation (RAG), and agent-based architectures.

• Codebase ownership: Build and maintain/review high-quality, efficient code in Python (using frameworks like LangChain/LangGraph) and SQL, focusing on reusable components, scalability, and performance best practices.

• Cloud integration: Aide in deployment of GenAI applications on cloud platforms (Azure, GCP, or AWS), optimizing resource usage and ensuring robust CI/CD processes.

• Cross-functional collaboration: Work closely with product owners, data scientists, and business SMEs to define project requirements, translate technical details, and deliver impactful AI products.

• Mentoring and guidance: Provide technical leadership and knowledge-sharing to the engineering team, fostering best practices in machine learning and large language model development.

• Core Stack Required:

• Software Engineering & GenAI (8+ YOE total, 2+ YOE GenAI): Production-grade distributed systems, RAG, and agent-based architectures.

• AI Frameworks & Python (5+ YOE): Expert Python proficiency with LangChain, LangGraph, or similar frameworks.

• Databases & Cloud (3+ YOE): SQL & NoSQL databases, vector databases (Pinecone, Weaviate, FAISS), and AWS/Azure/GCP deployment.