Senior Gen AI Architect

Space Inventive; Hyderabad; Hybrid; INR 2,600,000 - 3,800,000; Full time

Job summary

Space Inventive in Hyderabad seeks a senior AI/ML engineer to design and deploy next-generation agentic AI systems. You will work on large language models, multi-agent orchestration, memory, and tool integration in production environments.

You will mentor engineers, collaborate with product teams, and optimize prompts and MCPs, with hybrid work in India. The role emphasizes scalable architectures, cloud deployment, and cross-functional collaboration.

Qualifications

• BTech/MTech in Computer Science, Artificial Intelligence, or a related field.
• 6+ years of professional experience in AI/ML engineering with production-grade systems.
• Expert proficiency in Python and AI/ML frameworks (TensorFlow, PyTorch, Hugging Face).
• Strong experience in system design for scalable AI/ML and GenAI architectures.
• Hands-on experience with advanced agentic AI concepts such as planning, reasoning, tool use, memory management, and multi-agent systems.
• Experience implementing A2A protocols for distributed agent communication and coordination.
• Familiarity with Model Context Protocols (MCPs) or similar frameworks for context orchestration and tool integration.
• Deep understanding and practical experience with Large Language Models (LLMs).
• Proven expertise in prompt engineering, evaluation, and optimization techniques.
• Experience working with AWS cloud services for deploying and scaling AI solutions.

Responsibilities

• Design, architect, and deploy scalable agentic AI systems from concept to production.
• Lead system design for AI/ML and GenAI solutions ensuring scalability, reliability, and performance.
• Build and optimize advanced agentic workflows including multi-agent orchestration, memory, tool usage, and reasoning pipelines.
• Design and implement A2A communication protocols for seamless coordination between distributed AI agents.
• Integrate and manage MCPs to enable structured context sharing, tool interoperability, and dynamic knowledge access for LLM-based systems.
• Utilize and fine-tune LLMs to build intelligent, responsive, and scalable applications.
• Apply expert-level prompt engineering techniques to optimize model performance, accuracy, and efficiency.
• Develop and deploy AI solutions on AWS cloud infrastructure (ECS, Lambda, S3, Bedrock, API Gateway).
• Write clean, robust, and maintainable code in Python following best practices.
• Collaborate with cross-functional teams to define requirements and deliver high-quality AI features.
• Stay current with AI, ML, NLP, GenAI advancements; mentor junior engineers.

Skills

Python

TensorFlow

PyTorch

Hugging Face

LLM architectures

Agentic AI concepts

A2A protocols

MCPs

AWS cloud

Prompt engineering

Education

BTech/MTech in CS/AI or related field

Tools

AWS

Job description

Employment Type: Full-time

Work Mode: Hybrid

Experience: 8+ Years

About the Role:

We are seeking a highly skilled and innovative to join our dynamic team. In this role, you will be at the forefront of developing next-generation artificial intelligence solutions. You will specialize in designing and implementing sophisticated agentic AI systems and leveraging the power of Large Language Models (LLMs) to solve complex challenges. If you are passionate about building intelligent systems and want to make a significant impact, this is the perfect opportunity for you.

Key Responsibilities:

• Design, architect, and deploy scalable agentic AI systems from concept to production.
• Lead system design for AI/ML and GenAI solutions, ensuring scalability, reliability, and performance.
• Build and optimize advanced agentic workflows including multi-agent orchestration, memory, tool usage, and reasoning pipelines.
• Design and implement Agent-to-Agent (A2A) communication protocols for seamless coordination between distributed AI agents.
• Integrate and manage Model Context Protocols (MCPs) to enable structured context sharing, tool interoperability, and dynamic knowledge access for LLM-based systems.
• Utilize and fine-tune Large Language Models (LLMs) to build intelligent, responsive, and scalable applications.
• Apply expert-level prompt engineering techniques to optimize model performance, accuracy, and efficiency.
• Develop and deploy AI solutions on AWS cloud infrastructure (e.g., ECS, Lambda, S3, Bedrock, API Gateway).
• Write clean, robust, and maintainable code, primarily in Python, following best practices for software development.
• Collaborate with cross-functional teams, including product managers, data scientists, and engineers, to define requirements and deliver high-quality AI features.
• Stay current with the latest advancements in AI, machine learning, NLP, and GenAI ecosystems.
• Mentor junior engineers and contribute to a culture of technical excellence and continuous learning.

Required Qualifications and Skills:

• BTech/MTech in Computer Science, Artificial Intelligence, or a related field.
• 6+ years of professional experience in AI/ML engineering with a strong portfolio of production-grade systems.
• Expert proficiency in Python and AI/ML frameworks (TensorFlow, PyTorch, Hugging Face).
• Strong experience in system design for scalable AI/ML and GenAI architectures.
• Hands-on experience with advanced agentic AI concepts such as planning, reasoning, tool use, memory management, and multi-agent systems.
• Experience implementing A2A protocols for distributed agent communication and coordination.
• Familiarity with Model Context Protocols (MCPs) or similar frameworks for context orchestration and tool integration.
• Deep understanding and practical experience with Large Language Models (LLMs).
• Proven expertise in prompt engineering, evaluation, and optimization techniques.
• Experience working with AWS cloud services for deploying and scaling AI solutions.
• Strong problem-solving skills and analytical mindset.
• Excellent communication and collaboration skills in a hybrid work environment.

Good to Have:

• Familiarity with MLOps, CI/CD pipelines, and model monitoring.
• Exposure to multi-agent ecosystems, protocol standardization, and AI interoperability frameworks.