AI Engineer - Agentic AI

We are looking for an AI Engineer with strong hands-on experience in agentic AI, LLMs, LangChain, LangGraph, and multi-agent orchestration. You will work on building an autonomous Identity Harness designed to implement software features end-to-end, from Jira tickets through planning, coding, review, and testing.

We are looking for someone who has moved beyond basic chatbot/RAG development and has hands-on experience designing production-grade Agentic AI systems, particularly systems involving multi-agent orchestration, evaluation, governance, cost optimization, tool usage, and autonomous software development workflows.

Responsibilities:

• Build and orchestrate multi-agent AI workflows using LangChain, LangGraph, and similar frameworks.
• Develop agents for software design, action planning, coding, code review, and testing.
• Design workflows triggered by Jira tickets, converting requirements into epics/stories and routing them to specialized agents.
• Implement model routing, retry/fallback mechanisms, and token-cost optimization.
• Use non-LLM tools wherever possible to reduce unnecessary LLM usage and token consumption.
• Implement prompt-injection prevention, AI governance, context window, and memory management.
• Build RAGAS-based and automated evaluation pipelines for AI/LLM quality testing.
• Work with multiple AI/model environments, including Azure AI, AWS Bedrock, and similar platforms.
• Implement observability through monitoring, alerting, logging, and traceability.
• Enable human-in-the-loop intervention, including the ability to stop or terminate agent runs when required.

Requirements:

• 6+ years of overall software/AI engineering experience.
• Strong hands-on experience with generative AI/LLM applications.
• Strong experience with LangChain and LangGraph.
• Experience in Multi-Agent Orchestration / Agentic AI.
• Strong Python programming skills.
• Experience with RAG and LLM-based applications.
• Hands-on experience with RAGAS / LLM evaluation frameworks.
• Understanding of prompt injection prevention and AI guardrails.
• Experience with token optimization, model routing, context management, and memory management.
• Experience with AWS Bedrock, Azure AI/Azure OpenAI, or similar model platforms.
• Experience with tool calling/function calling and agent workflows.
• Strong understanding of LLM observability, monitoring, and evaluation.

Good to Have:

• Experience building coding agents / autonomous software-development agents.
• Experience with MCP, A2A, LangSmith, Langfuse, or similar technologies.
• Experience with automated code review and testing agents.
• Experience integrating Jira with AI/agentic workflows.
• Experience with retry, fallback, failure recovery, and human-in-the-loop architectures.
• Experience with Docker, Kubernetes, CI/CD, or cloud-native AI deployments.