Full Stack AI Engineer

Location: Work from Office (Noida)

Experience: 510 years (with strong hands-on AI/ML and full-stack development experience)

Role Summary

We are seeking a Full Stack AI Engineer to design, build, and deploy next-generation agentic AI applications leveraging Large Language Models (LLMs), multi-agent orchestration frameworks, and cloud-native AWS services. This role requires deep expertise in Python-based AI backends, LLM fine-tuning and integration, modern frontend frameworks, and scalable AWS deployments.

The ideal candidate will operate across the entire AI application lifecyclefrom model fine-tuning and agent workflow design to frontend development and production-grade cloud deployment.

Key Responsibilities

AI / Agentic Systems

• Design and implement multi-agent pipeline systems for complex reasoning, orchestration, and task execution.
• Develop and manage agentic workflows using frameworks such as LangChain, AWS Strands, or similar.
• Fine-tune and adapt LLMs using custom enterprise data on AWS Bedrock and/or OpenAI platforms.
• Implement advanced prompt engineering strategies for task decomposition, tool calling, and agent collaboration.

Backend Engineering

• Build and maintain Python-based backend APIs using Flask or FastAPI.
• Integrate LLM inference, vector search, memory, and agent logic into scalable backend services.
• Develop ML pipelines for data preprocessing, embedding generation, evaluation, and inference.
• Read, analyze, and interface with existing Java-based services or codebases as required.

Frontend Development

• Develop intuitive and responsive web interfaces using React.js or Vue.js.
• Integrate frontend components with AI-driven backend APIs for real-time inference and agent interactions.
• Collaborate with UX and product teams to translate AI workflows into usable customer experiences.

Cloud & Deployment

• Deploy and operate full-stack AI applications on AWS, leveraging:
• AWS Bedrock for LLM access and fine-tuning
• S3 for data and artifact storage
• Lambda for serverless workflows
• EC2 for scalable compute workloads
• Implement secure, scalable, and cost-optimized cloud architectures.
• Support CI/CD pipelines and production monitoring for AI services.

Required Skills

AI / ML

• Hands-on experience with LLM fine-tuning and inference (AWS Bedrock, OpenAI).
• Strong expertise in AI agent development and prompt engineering.
• Experience building production-grade GenAI applications.

Agent Frameworks

• Practical experience with LangChain, AWS Strands, or equivalent agent orchestration frameworks.

Backend Development

• Expert-level Python skills.
• Experience with Flask/FastAPI, ML pipelines, and large-scale data processing.
• Ability to read and analyze Java code for integration or enhancement.

Frontend

• Strong working knowledge of React.js or Vue.js.
• Experience building AI-integrated web applications.

Cloud (AWS)

• Hands-on experience with AWS Bedrock, S3, Lambda, EC2.
• Understanding of cloud security, scalability, and performance best practices.

Nice-to-Have Skills

• Deep experience in GenAI application development beyond PoCs.
• Exposure to multi-agent system architectures in production environments.
• Experience designing agentic workflows for enterprise-scale use cases.
• Familiarity with vector databases, embeddings, and retrieval-augmented generation (RAG).
• MLOps and model evaluation experience.