Sr. AI/ML Engineer

Role & responsibilities

• Design, implement, and optimize LLM-powered AI solutions for domain-specific use cases.
• Develop and maintain MCP sidecar servers that integrate seamlessly with existing NestJS architectures.
• Expose internal business logic as MCP tools/resources for integration with AI-enabled clients.
• Build and manage MLOps pipelines for LLM lifecycle training, deployment, monitoring, and retraining.
• Implement robust validation, observability, and security measures in both MCP tools and AI systems.
• Collaborate with cross-functional teams to integrate AI/LLM capabilities into production workflows.
• Maintain clear documentation, test suites, and deployment automation for AI and MCP components.
• Leverage third-party APIs and design scalable architectures to extend AI and MCP system capabilities.

Mandatory Requirements

• Education:

• Bachelors degree or higher in Computer Science, AI, Data Science, or related fields.
  

• AI/LLM Expertise:

• Development and deployment of Large Language Model (LLM)based applications.
• Experience fine-tuning and integrating open-source and proprietary LLMs for domain-specific use cases.
• Proficient with LLM frameworks/libraries (e.g., Hugging Face Transformers, LangChain, LlamaIndex).
• Experience with prompt engineering, RAG (Retrieval-Augmented Generation), and agent-based AI systems.
  

• MCP Server & Integration Skills:

• Strong understanding of the Model Context Protocol (MCP).
• Ability to expose NestJS services as MCP tools and resources with schema validation (e.g., zod).
• Knowledge of streamable HTTP transport for MCP where applicable.
• Proficiency in TypeScript/JavaScript and Python for MCP server development, LLM integration, and automation.
  

• MLOps Expertise:

• Hands-on experience with MLflow, Kubeflow, or equivalent for model tracking, deployment, and monitoring.
• Implement CI/CD pipelines for LLM and AI application delivery.
• Experience in containerizing AI applications (Docker) and deploying on cloud platforms (AWS, GCP, Azure).
• Knowledge of scalable inference serving (e.g., FastAPI, BentoML, vLLM, Ray Serve).