Job Title: AI Developer / Agentic AI Engineer

Role Type: Full-Time

About the Role

We are seeking an experienced and hands-on AI Developer to design, build, and scale advanced agentic AI capabilities. Working closely with the AI Architect, backend developers, UI engineers, product managers, QA, and SRE teams, you will be responsible for implementing complex agent workflows, tool integrations, robust prompt logic, evaluation datasets, and production-grade LLM observability. This role is focused on the end-to-end development of LangGraph-based workflows, Azure OpenAI / Azure AI Foundry integrations, MCP (Model Context Protocol) tool calling, and continuous performance monitoring for consumer-facing AI products.

Key Responsibilities

Agentic Workflow & Core Development

- Design, build, and maintain production-grade agentic workflows using LangGraph and related orchestration frameworks.
- Implement sophisticated agent mechanics including intent routing, state management, conditional branching, fallback strategies, and human-in-the-loop escalation logic.
- Develop and maintain system instructions, reusable prompt templates, and structured prompt versioning protocols.

Tool Integration & Architecture
- Integrate AI agents with internal backend services and external APIs using Model Context Protocol (MCP) or structured tool contracts.
- Collaborate with backend engineers to define robust input/output schemas for tool calling and secure data exchange.

Observability, Evaluation & Testing
- Implement comprehensive LLM observability, tracing, and evaluation hooks to monitor latency, token usage, failures, and execution quality.
- Create and curate test datasets for rigorous AI workflow validation and regression testing.
- Evaluate model outputs for accuracy, relevance, groundedness, safety, and task completion.




- Troubleshoot and debug complex LLM behaviors, tool failures, and response latency alongside QA and SRE teams.

Compliance & Security
- Ensure all AI workflows and integrations strictly adhere to enterprise data privacy, security standards, and responsible AI guidelines.

Required Skills & Experience
- Hands-on qualified experience building and deploying production-grade LLM-based applications.
- Strong proficiency in Python development and integrating with REST APIs.
- Proven expertise with agent orchestration frameworks such as LangGraph, LangChain, Semantic Kernel, or equivalent.
- Deep understanding of agentic concepts: intent routing, state persistence, tool calling, workflow orchestration, fallback handling, and human-in-the-loop flows.
- Hands-on experience with model platforms including Azure OpenAI, Azure AI Foundry, or OpenAI APIs.
- Familiarity with prompt design methodologies, prompt versioning, and prompt testing.
- Working knowledge of authentication, secure API calls, data privacy, and LLM application tracing/monitoring.
- Strong collaborative skills with the ability to translate architectural designs from AI Leads into executable agent flows.

Nice to Have

- Hands-on implementation experience with Azure AI Foundry and Model Context Protocol (MCP).
- Familiarity with LLM observability and evaluation tools (e.g., Azure Monitor, Application Insights, Langfuse, OpenTelemetry, PromptFlow).
- Experience building AI evaluation datasets and testing suites.
- Exposure to RAG architectures, Azure AI Search, vector databases, and grounding patterns.
- Experience implementing content safety guardrails, hallucination mitigation, and responsible AI practices.
- Background in consumer-facing portals, CRM systems, contact centers, or digital assistant platforms.
- Basic understanding of .NET or Azure backend services.

Share your resume at [email protected]

📌 Senior AI Engineer (India)
🏢 Edge
📍 India