Principal Engineer

Overview

Build, scale, and optimize cloud generative AI applications, with a focus on production-grade Retrieval-Augmented Generation (RAG) pipelines, Python production code, and secure cloud deployment.

What you'll do

• Design, implement, and optimize production-grade Retrieval-Augmented Generation (RAG) pipelines to improve LLM accuracy.
• Write clean, modular, and highly efficient backend code using Python frameworks like FastAPI or LangChain.
• Deploy, secure, and scale GenAI applications on cloud platforms (AWS, GCP, or Azure).
• Manage and tune Vector Databases to ensure fast, relevant semantic search retrieval.
• Connect application frontends and internal data systems with enterprise LLMs via secure APIs.
• Track LLM token usage, response latency, and retrieval accuracy in production.

What you'll need

• 5–6+ years of cloud engineering experience and AI solution development.
• Expert-level Python skills, with a focus on asynchronous programming and API development.
• Hands-on experience using frameworks like LangChain, LlamaIndex, Hugging Face or any similar framework.
• Practical experience with databases such as Vespa, Pinecone, Milvus, Chroma, or any similar database.
• Proven experience in deploying and managing cloud compute (Docker, Kubernetes) and serverless services.
• Ability to systematically design and optimize prompts for specific business use cases.
• Bachelor’s degree in Computer Science, Software Engineering, or a related technical field.

Nice to have

• Familiarity with fine-tuning open-source LLMs (e.g., Llama, Mistral).
• Experience setting up MLOps/LLMOps tracking tools (e.g., LangSmith, Weights & Biases).
• Cloud certifications focusing on DevOps or Developer pathways.

Details

• Location: Bengaluru, India.
• Work mode: Onsite.