AI Engineer

We are seeking a highly skilled AI Engineer with 5+ years of experience to lead the design, development, and optimization of cutting-edge generative AI solutions. In this role, you will leverage advanced LLM architectures, automation frameworks, and cloud infrastructure to build scalable, cost-efficient AI applications.The ideal candidate has a deep understanding of Anthropic's Claude ecosystem (including Opus, Artifacts, and specialized prompt engineering controls like EffortLevel), next-generation coding paradigms (UltraCode), and robust cloud/automation pipelines (Azure, n8n).

Key Responsibilities

• AI Architecture & Implementation: Design and deploy advanced AI workflows using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks.
• Claude Ecosystem Expertise: Utilize Anthropic’s model family (including Claude Opus) alongside specialized platform features like Claude Artifacts and Claude Design principles to build interactive, state-of-the-art user experiences.
• System Integration: Interface with and manage integrations across diverse AI architectures, model environments, and developer suites (including Codex, Luna, Terra, Sol, and Astra frameworks).
• Cost & Performance Optimization: Implement strict token cost optimization strategies, context window management, and inference latency reduction techniques.
• Workflow Automation & Cloud DevOps: Build complex, automated backend workflows using n8n. Deploy, scale, and maintain AI infrastructure securely within the Azure cloud environment.
• CI/CD & Version Control: Manage codebase integrity, branching strategies, and deployment pipelines using GitHub.
• Advanced Prompting & Control: Master complex prompt design utilizing parameters like execution effort levels (EffortLevel) and advanced synthetic code generation paradigms (UltraCode).

Required Skills & Qualifications

• Core Experience: Minimum 5 years of professional software engineering experience, with at least 2–3 years dedicated heavily to Generative AI and LLM application development.
• Model Expertise: Deep hands-on experience with Anthropic models (Claude Opus), OpenAI models (Codex architectures), and associated ecosystem layers (Luna, Terra, Sol, Astra).
• Advanced AI Concepts: Proven track record building production-grade RAG pipelines, vector database integrations, and semantic search systems.
• Optimization & Controls: Deep expertise in token reduction strategies, structured outputs, prompt caching, and managing model execution limits (EffortLevel / UltraCode paradigms).
• Tools & Infrastructure:
• Strong workflow automation skills using n8n.
• Cloud deployment experience on Microsoft Azure (Azure OpenAI Service, VMs, App Services).
• Highly proficient with GitHub for version control and CI/CD pipelines.
• Soft Skills: Excellent problem-solving abilities, strong communication skills, and a self-driven attitude suitable for a fast-paced environment.

Pay: ₹1,000,000.00 - ₹1,500,000.00 per year

Work Location: In person