Generative AI Engineer

Role Overview

We are looking for a Generative AI Engineer to build, optimize, and productions cutting-edge AI systems. You will focus heavily on backend AI orchestration, framework integration, and model performance. In this role, you will take advanced RAG workflows and multi-agent concepts and turn them into scalable, production-grade enterprise software.

Key Responsibilities

• AI Orchestration: Build, test, and optimize bespoke Agentic AI solutions and multi-agent workflows.
• Core Product Integration: Co-develop integration pipelines to embed core AI models into client environments.
• Technical Delivery: Own the technical lifecycle of AI applications from rapid prototype to stable production release.
• Optimization & Debugging: Perform technical debugging, root-cause analysis, and latency/prompt optimizations.
• Best Practices: Implement engineering best practices for LLM evaluation, guardrails, and version control.
• Risk Management: Identify and flag model drift, data leakage, and system risks early.

Technical Requirements

• GenAI Ecosystem: 2+ years of hands-on experience building production RAG pipelines and multi-agent systems using LangChain, LangGraph, or LlamaIndex.
• Protocols & Frameworks: Strong understanding of Model Context Protocols (MCP), A2A protocols, and Agent Developer Kits.
• LLM Engineering: Practical proficiency in prompting techniques, fine-tuning workflows, and evaluating LLM outputs.
• Data Science Stack: Strong hands-on experience leveraging Python, pandas, scikit-learn, and PyTorch.
• Cloud & MLOps: Experience deploying and scaling machine learning solutions on AWS, Azure, or GCP.
• DevOps & Containers: Working knowledge of Docker, Kubernetes, CI/CD pipelines, and GitHub Actions.

Backend Stack: Production-grade backend coding skills in Python, with basic familiarity in JavaScript/TypeScript for API