Senior Data Software Engineer with ML and RAG, AI Data Platform

**Senior Data Software Engineer with ML and RAG, AI Data Platform

Key Responsibilities**

• System Architecture: Designing end-to-end AI applications, focusing on scalable infrastructure, reliability, and security.
• Model Implementation & RAG: Implementing Retrieval-Augmented Generation (RAG) pipelines, advanced prompt engineering, and fine-tuning models (HuggingFace, GPT-4)
• Production Deployment: Moving models from research to production using CI/CD pipelines (GitHub Actions), Docker, and Kubernetes.
• Agentic Workflows: Developing autonomous agents for complex task automation using tools like LangChain/LangGraph.
• Agent Driven Development Experience: Utilized coding agents (Claude Code, Copilot etc) for faster development iteration.
• Mentorship & Best Practices: Guiding junior engineers on coding standards, ensuring high-quality, maintainable code, and establishing AI development best practices.
• Data Pipeline Engineering: Structuring, cleaning, and preprocessing data for model training and retrieval.

Tech Stack

• Languages: Python (Primary), TypeScript/JavaScript (for full-stack integration, good to have).
• Frameworks & Libraries: PyTorch, TensorFlow, HuggingFace Ecosystem, LangChain/LangGraph.
• AI/LLM APIs: OpenAI, Anthropic, Azure AI.
• Vector Databases & Retrieval: ChromaDB, Pinecone, Weaviate, Milvus.
• MLOps & DevOps: Docker, Kubernetes, Terraform, GitHub Actions, FastAPI.
• Cloud Platforms: AWS Bedrock, Azure AI, Vertex AI
• Assisted Coding Agents: Claude Code, Copilot, Codex.