AI Engineer

Netfolks Consulting; Dehradun; On-site; INR 1,800,000 - 2,400,000; Full time

Job summary

Netfolks Consulting is seeking a Senior AI Engineer in Dehradun, India to design and implement next-generation autonomous AI systems. You will architect multi-agent workflows where AI personas collaborate, self-correct, and integrate with human stakeholders to solve enterprise problems.

The role goes beyond simple prompts, focusing on cyclic agent orchestration, automated code generation, and HITL verification within secure testing environments.

Responsibilities

• Design and deploy enterprise-grade multi-agent architectures using stateful, cyclic frameworks (e.g., LangGraph, AutoGen, CrewAI).
• Build HITL workflows that pause, solicit user feedback, process structured inputs, and resume execution.
• Develop robust text-to-code and code-generation pipelines, ensuring output accuracy through automated verification and testing layers.
• Implement structured data parsing (JSON formatting, Pydantic validation) to guarantee reliable communication interfaces between AI agents.
• Optimize context windows and Retrieval-Augmented Generation (RAG) strategies to manage long-term state across complex workflows.
• Establish secure, sandboxed execution environments (e.g., Docker) for automated testing, evaluation, and iteration of AI-generated outputs.

Job description

We are seeking a highly skilled Senior AI Engineer to design and implement next-generation autonomous AI systems. In this role, you will architect complex, multi-agent workflows where specialized AI personas collaborate, self-correct, and integrate with human stakeholders to solve complex enterprise problems. If you have deep experience moving beyond simple chat prompts into cyclic, stateful agent orchestration and automated code generation, we want to hear from you.

Key Responsibilities

• Design and deploy enterprise-grade multi-agent architectures using stateful, cyclic frameworks (e.g., LangGraph, AutoGen, CrewAI).
• Build advanced Human-in-the-Loop (HITL) workflows that allow AI agents to dynamically pause, solicit user feedback, process structured inputs, and resume execution.
• Develop robust text-to-code and code-generation pipelines, ensuring output accuracy through automated verification and testing layers.
• Implement structured data parsing (JSON formatting, Pydantic validation) to guarantee reliable communication interfaces between different AI agents.
• Optimize context windows and implement advanced Retrieval-Augmented Generation (RAG) strategies to manage long-term state across complex workflows.
• Establish secure, sandboxed execution environments (e.g., Docker) for automated testing, evaluation, and iteration of AI-generated outputs.