Role : AI Lead Agent Development Platform (ADP)

Experience : 15+ Years

Location : Remote (India)

Employment Type : Payroll of Haparz (Direct Contract)

About the Role :

We are seeking an experienced AI Lead to drive the AI engineering track for an enterprise-grade Agent Development Platform (ADP).

This is a hands-on leadership role responsible for defining the architecture, evaluation frameworks, AI security posture, and engineering standards for production-scale Agentic AI systems.

The ideal candidate should have strong experience in building LLM-powered applications, multi-agent systems, RAG architectures, AI evaluation frameworks, and leading engineering teams delivering complex AI solutions.

Roles & Responsibilities :

- Lead the architecture and technical direction for Agentic AI and multi-agent platforms.

- Define agent frameworks, orchestration strategies, memory management, and model routing policies.

- Design and establish standard agent architectures, including planner-executor patterns, tool usage protocols, and Human-in-the-Loop (HITL) workflows.

- Build and own AI evaluation frameworks, including golden datasets, field-level accuracy metrics, regression testing, and release quality gates.

- Drive AI security initiatives, including prompt injection prevention, tool authorization controls, and adversarial testing.

- Architect and develop high-impact components such as agent SDKs, evaluation harnesses, and production-grade AI agents.

- Define RAG strategies, knowledge graphs, embedding pipelines, and secure multi-tenant data architectures.

- Establish LLMOps practices, including observability, tracing, quality monitoring, and cost optimization.

- Lead and mentor AI engineering teams, establish reusable frameworks, and drive engineering excellence.

- Collaborate with client stakeholders, CTOs, and architecture boards to define and defend technical decisions.

Required Experience :

- 15+ years of software engineering experience with 3+ years building production-grade LLM applications.

- Proven experience building Agentic AI platforms or multi-agent systems supporting real business use cases.

- Strong expertise in Python and modern AI engineering practices.

- Hands-on experience with LangGraph, Claude Agent SDK, LangChain, LangSmith, AWS Bedrock, and Anthropic models.

- Experience with RAG, Knowledge Graphs, Neo4j, PGVector, Temporal, LiteLLM, and Langfuse.

- Strong understanding of AI evaluation frameworks, hallucination measurement, prompt engineering, and AI security practices.

- Experience implementing observability, evaluation-gated CI/CD, and cost monitoring for AI systems.

- Proven experience leading engineering teams and delivering large-scale, milestone-driven programs.

Preferred Experience :

- Exposure to Commercial Real Estate, Legal, Insurance, Financial Services, or other document-intensive domains.

- Experience working with SOC2, GDPR, FedRAMP, or similar compliance frameworks.

- Contributions to AI communities, open-source projects, publications, or conference presentations are an added advantage.