Description

You will design and scale Agentic AI systems for application modernization, defining product vision and leading engineering teams.

This role is on-site.

Responsibilities

• Architect agentic AI systems, including reference architectures for container-based hosting, vector DB memory management, and data pipelines.
• Define product vision for reusable AI modules, RAG, hybrid ML/LLM systems, and standardized evaluation frameworks.
• Select the LLM stack, including models, orchestration frameworks, and observability tools, based on cost, latency, and performance.
• Lead and recruit a GenAI engineering team while serving as the primary SME for customer engagements and internal leadership.
• Collaborate with security teams to enforce AI safety, data privacy, and ethical AI practices.

Required Skills

• 10+ years of experience in AI/ML engineering.
• 1+ years of experience specifically in agentic AI and LLM systems.
• Strong proficiency in LangGraph, LangMem, and agentic workflow development.
• Extensive experience in LLM evaluation and testing using LangGraph evals, Agent evals, DeepEval, or prompt testing frameworks.
• Hands-on experience with GitHub Copilot and Claude Code for rapid prototyping.
• Expertise in reasoning, instruct, safety, and embedding models.
• Proficiency with at least one major cloud platform: AWS, Azure, or GCP.
• Experience embedding LLM workflows into existing enterprise systems.

Preferred Skills

• Standardize advanced prompting patterns such as chain-of-thought, few-shot templates, and automated chunking.

Key Skills

Education

Any Gradute