Job Overview

We are looking for a highly skilled and innovative AI Engineer with a minimum of 5 years of experience to design, build, and deploy production-grade Artificial Intelligence and Large Language Model (LLM) architectures.In this role, you will lead the design of AI systems, optimize token usage and inference costs, and build advanced automated workflows. You will bridge the gap between traditional software engineering, cloud architecture, and cutting-edge generative AI models.

Key Responsibilities

- AI Architecture & Design: Create and review system blueprints, technical designs, and AI artifacts to ensure scalable, secure, and production-ready deployments.
- Token & Cost Optimization: Implement advanced optimization techniques for managing context windows, prompt compression, and token cost optimization across high-throughput LLM pipelines.
- Workflow Automation: Design and build complex, agentic AI workflows and integrations using orchestration engines like n8n.
- Model Implementation: Work deeply with state-of-the-art models (including Anthropic's Claude Opus, Claude 3.5 Sonnet / Claude Code) and specialized architectures like Codex, Luna Terra, and Sol Astra.
- Cross-Functional Development: Write high-performance backend code, integrate AI models into existing enterprise ecosystems, and maintain high standards of code quality.
- DevOps & Infrastructure: Manage version control, CI/CD pipelines, and team-oriented workflows through GitHub, deploying applications natively onto the Azure cloud platform.

Requirements & Qualifications

- Experience: Minimum 5+ years of professional software engineering and AI systems development experience.




- Core Languages: Proficiency in high-performance and object-oriented programming with strong hands-on experience in C++ and Java.
- Cloud & DevOps: Proven experience architecting and managing AI workloads on Azure Cloud Services, alongside advanced workflows using GitHub.
- AI & LLM Technical Skills:
- Strong familiarity with advanced prompt engineering, RAG (Retrieval-Augmented Generation), and token tracking/budgeting.
- Practical experience building automated nodes and workflows inside n8n.
- Deep understanding of modern code generation assistants (like Claude Code) and foundational code models.
- Familiarity or direct project exposure involving specialized frameworks or ecosystems like Luna Terra and Sol Astra.
- Education: Bachelor’s or Master’s degree in Computer Science, Data Science, AI, or a closely related quantitative field.

Position Details

- Location: On-site at Janakpuri, New Delhi (Assuming alignment with previous role)
- Days & Hours: Monday to Saturday | 9:30 AM to 6:30 PM
- Employment Type: Full-time

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

Application Question(s):

- Question: How many years of professional experience do you have in software engineering and AI systems development?
- Which language pair do you have strong backend production experience with?
- Have you built complex agentic workflows using n8n?
- In 2-3 sentences, explain your approach to token cost optimization in a high-throughput LLM application.
- Are you comfortable working full-time, fully on-site in Janakpuri, New Delhi, with a Monday to Saturday (9:30 AM – 6:30 PM) schedule?

Work Location: In person

📌 AI Engineer (Janakpuri)
🏢 OSS Education
📍 Janakpuri