Junior Chatbot Software Engineer

• Take full-stack ownership from hardware to user facing application
• Provision, configure and maintain GPU servers and related hardware resources
• Select, install and optimize ML framework and model weights for on-prem inference/training
• Build and deploy model-serving infrastructure (APIs, scaling, batching, monitoring)
• Implement secure data pipelines, preprocessing, and storage for training
• Integrate chatbot models with internal applications, authentication, and messaging platform

Requirements

• Experience with open-source LLMs such as GPT_OSS, LLaMA, Mistral, Falcon, Phi, Gemma, etc.
• Proficiency with LLM inference frameworks: Ollama, XInference, vLLM, llama.cpp, HuggingFace Transformers, etc.
• Knowledge of Retrieval-Augmented Generation (RAG) pipelines
• Familiar with fine-tuning techniques and prompt engineering
• Experience with vector databases: PGVector, Elastic Search & Kibana, Chroma, Weaviate, Qdrant, Milvus, FAISS, Mongo, etc.
• Strong proficiency in Python (primary language for AI/ML development)
• Experience with FastAPI, Flask, or Django for API development
• Familiar with C#, Node.js or Java/Go is a plus
• RESTful and WebSocket API design and implementation
• Integration with chat interfaces: Teams, Slack, web widgets, or custom portals
• Evaluation and testing of LLM output quality