Posted 12 June, 2026
Agentic AI Engineer
NR Consulting - India
Trivandrum, Kochi, Pune, Bangalore, IN
Full Time
Reference: 26-04385-2220-1
Title: Agentic AI Engineer
Location: Trivandrum, Kochi, Pune, Bangalore
Exp: 6+ yrs
Job Description:
Key Responsibilities
• AI Agent Design & Development: Design and implement production-ready AI Agents using the Google Agent Development Kit (ADK) or Lang Graph. Build agents capable of multi-step reasoning, tool invocation, and context-aware decision making to automate complex data engineering tasks.
• MCP Integration: Integrate agents with enterprise tools and knowledge sources using the Model Context Protocol (MCP). Develop and maintain MCP Servers (e.g., GCS MCP Server, Big Query MCP Server) to expose structured data and services as agent-consumable tools.
• GCP Services Integration: Build and manage integrations with core GCP services including Google Cloud Storage (GCS), Big Query, Vertex AI Model Garden, and Cloud Run. Ensure agents can securely read/write data from GCS buckets, query and update Big Query tables, and invoke LLM endpoints on Vertex AI.
• Production Deployment: Deploy AI agents to production environments on GCP using Cloud Run or equivalent services. Implement CI/CD pipelines, containerization, and infrastructure-as-code practices to ensure repeatable and reliable deployments.
• Evaluation & Quality Assurance: Design and implement comprehensive evaluation strategies for AI agents, including automated unit and integration tests, LLM output quality evaluations, and AgentOps monitoring pipelines. Define and track metrics for agent accuracy, latency, and reliability.
• Prompt Engineering & Context Management: Craft, version, and manage prompt templates for diverse agent workflows. Implement context assembly strategies including retrieval-augmented generation (RAG) and dynamic context loading via MCP to maximize LLM response quality.
• Observability & Monitoring: Instrument agents with logging, tracing, and alerting to support production observability.
• Collaboration: Work closely with data engineers, ML engineers, and solution architects to understand business requirements and translate them into robust agentic workflows. Participate in design reviews and contribute to best practices for AI agent development.
Skills & Qualifications
Required:
• Minimum 1 year of hands-on experience building, deploying, and operating AI Agents in a production environment.
• Proficiency in Python for agent development, API integration, and cloud scripting.
• Proven experience integrating with GCP services, with depth in Google Cloud Storage (GCS) and BigQuery (BQ) — including schema management, querying, and data loading workflows.
• Solid understanding of Large Language Model (LLM) concepts including prompt engineering, context window management, tool/function calling, and chain-of-thought reasoning.
• Experience designing and executing evaluation strategies for AI/LLM-based systems, including automated testing, output validation, and quality benchmarking.
• Familiarity with the Model Context Protocol (MCP) or equivalent tool-use / function-calling frameworks for connecting AI agents to external systems and knowledge bases.
• Experience with containerization and deployment on GCP (e.g., Cloud Run, Docker, Cloud Build).
• Strong understanding of RESTful API design, JSON data formats, and microservices architecture.
Location: Trivandrum, Kochi, Pune, Bangalore
Exp: 6+ yrs
Job Description:
Key Responsibilities
• AI Agent Design & Development: Design and implement production-ready AI Agents using the Google Agent Development Kit (ADK) or Lang Graph. Build agents capable of multi-step reasoning, tool invocation, and context-aware decision making to automate complex data engineering tasks.
• MCP Integration: Integrate agents with enterprise tools and knowledge sources using the Model Context Protocol (MCP). Develop and maintain MCP Servers (e.g., GCS MCP Server, Big Query MCP Server) to expose structured data and services as agent-consumable tools.
• GCP Services Integration: Build and manage integrations with core GCP services including Google Cloud Storage (GCS), Big Query, Vertex AI Model Garden, and Cloud Run. Ensure agents can securely read/write data from GCS buckets, query and update Big Query tables, and invoke LLM endpoints on Vertex AI.
• Production Deployment: Deploy AI agents to production environments on GCP using Cloud Run or equivalent services. Implement CI/CD pipelines, containerization, and infrastructure-as-code practices to ensure repeatable and reliable deployments.
• Evaluation & Quality Assurance: Design and implement comprehensive evaluation strategies for AI agents, including automated unit and integration tests, LLM output quality evaluations, and AgentOps monitoring pipelines. Define and track metrics for agent accuracy, latency, and reliability.
• Prompt Engineering & Context Management: Craft, version, and manage prompt templates for diverse agent workflows. Implement context assembly strategies including retrieval-augmented generation (RAG) and dynamic context loading via MCP to maximize LLM response quality.
• Observability & Monitoring: Instrument agents with logging, tracing, and alerting to support production observability.
• Collaboration: Work closely with data engineers, ML engineers, and solution architects to understand business requirements and translate them into robust agentic workflows. Participate in design reviews and contribute to best practices for AI agent development.
Skills & Qualifications
Required:
• Minimum 1 year of hands-on experience building, deploying, and operating AI Agents in a production environment.
• Proficiency in Python for agent development, API integration, and cloud scripting.
• Proven experience integrating with GCP services, with depth in Google Cloud Storage (GCS) and BigQuery (BQ) — including schema management, querying, and data loading workflows.
• Solid understanding of Large Language Model (LLM) concepts including prompt engineering, context window management, tool/function calling, and chain-of-thought reasoning.
• Experience designing and executing evaluation strategies for AI/LLM-based systems, including automated testing, output validation, and quality benchmarking.
• Familiarity with the Model Context Protocol (MCP) or equivalent tool-use / function-calling frameworks for connecting AI agents to external systems and knowledge bases.
• Experience with containerization and deployment on GCP (e.g., Cloud Run, Docker, Cloud Build).
• Strong understanding of RESTful API design, JSON data formats, and microservices architecture.
