Artificial Intelligence Engineer

Responsibilities

• Design, develop, and deploy enterprise-grade Agentic AI and Generative AI applications using LLMs, RAG pipelines, prompt engineering, and multi-agent frameworks.
• Build scalable AI-powered backend services and APIs using Python or Java/Spring Boot, integrating AI capabilities into enterprise applications.
• Develop intelligent workflows using Amazon Bedrock, OpenAI, LangChain/LangGraph, vector databases, and enterprise APIs.
• Build and optimize RAG solutions, AI agents, tool calling, prompt orchestration, and structured output pipelines.
• Develop REST APIs and microservices to integrate AI solutions with enterprise systems and business applications.
• Evaluate, fine-tune, test, and optimize LLM performance while implementing AI guardrails and responsible AI practices.
• Collaborate with product owners, architects, and engineering teams to deliver scalable, production-ready AI solutions.
• Mentor developers on AI best practices and contribute to the adoption of AI across enterprise applications.

Required Skills

• Strong hands-on experience with Agentic AI, Generative AI, LLMs, RAG, Prompt Engineering, and AI Agents
• Experience with Amazon Bedrock, OpenAI APIs, LangChain/LangGraph, MCP, or similar AI frameworks
• Strong programming experience in Python and/or Java with Spring Boot
• Experience building REST APIs, microservices, and integrating enterprise applications
• Experience with Vector Databases (Pinecone, Chroma, FAISS, Weaviate, or similar)
• Knowledge of Kafka or other event-driven messaging platforms is a plus
• Basic familiarity with AWS and Docker for deploying AI applications
• Experience with Git and CI/CD workflows
• Strong problem-solving, communication, and collaboration skills

Preferred

• Experience with AI evaluation frameworks, guardrails, model monitoring, and prompt optimization.
• Exposure to GraphRAG, Knowledge Graphs, or autonomous agent frameworks is a plus.