Job Description
AI Software Engineer (Agentic AI & MCP Systems)
Key Responsibilities
- Design, develop, and maintain MCP servers using Python and/or TypeScript to support scalable and standardized LLM interactions.
- Build and deploy agentic AI systems capable of planning, reasoning, and executing multi-step workflows.
- Implement agent workflows using:
- Tool / function calling
- Short-term and long-term memory
- Context management
- Guardrails and controlled execution
- Develop system with agents orchestrates workflows with LLMs acting as the reasoning and decision-making layer.
- Build Retrieval-Augmented Generation (RAG) pipelines, including:
- Document ingestion and chunking strategies
- Embedding generation and vector storage
- Vector search and hybrid retrieval
Implement Knowledge Graph–based solutions, including Graph RAG, to enable reasoning over structured and unstructured enterprise data.
- Design and deploy AI systems on cloud infrastructure, with strong experience in AWS Bedrock and related AWS services.
- Ensure adherence to SDLC best practices, including design, implementation, testing, deployment, monitoring, and maintenance.
- Write clean, modular, well-documented code and participate in code reviews and architectural discussions.
Required Skills & Qualifications
- Strong development experience in Python and/or TypeScript.
- Hands-on experience building MCP servers or equivalent LLM integration layers.
- Experience with AI agent frameworks (e.g., LangGraph/LangChain, CrewAI etc.).
- Prior working experience with AI-powered IDE platforms, such as:
- GitHub Copilot
- Cursor
- Windsurf
- Claude Code
- Kiro
- or similar tools available in the market
- Experience designing and deploying AI/LLM systems on AWS cloud platform, especially AWS Bedrock.
- Strong understanding of LLM architectures, prompt design, tool usage, memory, and orchestration.
- Hands-on experience with vector databases, embeddings, and RAG optimization techniques.
- Solid foundation in software engineering principles and the software development life cycle (SDLC).
- Experience with REST APIs, microservices, and system integration patterns.
- Proficiency with Git-based workflows and CI/CD pipelines.
Good-to-Have Skills
- Experience with spec-driven development or requirements-driven engineering.
- Familiarity with observability, evaluation, and monitoring of LLM and agent behavior.
- Exposure to AI security, governance, and responsible AI practices.
