Job Description

Job Title: RAG-Based Chatbot Developer (GCP + LLM Focus)

Location: Noida Job Type: Full-time

Experience Level: Mid to Senior Level Industry: AI/ML | SaaS | Cloud Platforms

Key Responsibilities:

? Architect and develop RAG-based chatbot systems using GCP-native services and Python.

? Orchestrate multi-turn dialogues using RASA, integrated with retrieval layers and vector databases.

? Build and manage ingestion pipelines using LlamaIndex, FAISS, ChromaDB, or Pinecone, deployed within GCP environments.

? Integrate and experiment with GCP Model Garden and Vertex AI Flash models for fast, production-grade inference.

? Work with both open-source LLMs and hosted inference APIs--deploy models or access APIs securely within Vertex AI or custom GKE environments.

? Collaborate on backend services (built in Django) to connect the chatbot with data sources, admin tools, and client-facing APIs.

? Deploy, scale, and manage services using Cloud Run, GKE, Pub/Sub, Cloud Functions, and Terraform.

? Monitor performance and reliability using Cloud Logging, Cloud Monitoring, and CI/CD pipelines on Cloud Build.

? Stay curious--test new models, evaluate prompt strategies, and prototype ideas using Colab, Vertex AI Notebooks, and sandbox environments.

Required Skills

? Must Have:
? Strong experience with RASA or similar open-source chatbot orchestration frameworks. ? Proficiency in Python with working knowledge of Django backend basics.
? Experience building vector search pipelines with LlamaIndex, LangChain, and deploying them with vector databases.
? Deep familiarity with Google Cloud Platform, including Cloud Run, GKE, and Vertex AI.
? Hands-on experience using Model Garden, Vertex AI Flash models, and managing inference workflows on GCP.

Interested candidates can share their CV sakshisharma@plutos.one

Job Types: Full-time, Permanent

Pay: ₹300,000.00 - ₹700,000.00 per year

Benefits:

Health insurance Paid sick time Provident Fund
Work Location: In person