AI full Stack Engineer (LLM) l 12-month contract

Responsibilities:

• Take ownership of an existing AI-powered application through structured knowledge transfer, including understanding and documenting architecture, codebase, and integrations
• Provide ongoing application support including bug fixing, enhancements, incident resolution, performance tuning, and stability improvements
• Design, develop, and deploy end-to-end AI applications using LLMs, RAG, and agentic frameworks
• Build MCP-based tool integrations and agentic workflows to connect AI solutions with enterprise systems and processes
• Translate business requirements into scalable AI-powered solutions with robust backend and frontend design
• Develop and integrate APIs, application logic, and user-facing features for AI-driven use cases
• Implement monitoring, observability, and evaluation mechanisms for AI models, prompts, and agent behavior
• Collaborate with cross-functional stakeholders to deliver production-ready solutions aligned with business outcomes
• Contribute to application design, code quality, testing, CI/CD, and engineering best practices

Requirements

• Bachelor’s degree in Computer Science or a related discipline
• Minimum 2 years of experience in full stack software engineering with production application exposure
• Proven experience building AI agents or multi-agent systems using frameworks like LangChain, LlamaIndex, LangGraph, AutoGen, or CrewAI
• Hands-on experience with LLMs, RAG architectures, agentic design patterns, and deploying generative AI applications
• Familiarity with MCP integrations, AI guardrails, application evaluation, and LLMOps practices
• Understanding of prompt engineering, model evaluation, AI observability tools (e.g., LangSmith), and responsible AI
• Solid software engineering skills including clean code, testing, design patterns, REST APIs, CI/CD, and containerization
• Proficiency in Python, TypeScript, React / Next.js, and Tailwind CSS
• Experience with relational and NoSQL databases, including schema design and query optimization
• Familiarity with vector databases and semantic search for RAG applications
• Hands-on experience with AWS services such as Lambda, API Gateway, S3, CloudWatch, and IAM
• Experience with AWS Bedrock, including foundation models, Knowledge Bases, Agents, and Guardrails