Description

You will lead the architecture and implementation of agentic AI systems and multi-agent workflows.

This role is remote.

Responsibilities

• Architect agentic AI chat systems integrating LLMs with tools, APIs, and memory for dynamic task execution.
• Design and develop LangGraph-based workflows to orchestrate multi-step, multi-agent interactions.
• Build reference architectures, POCs, and technical documentation to guide engineering teams.
• Ensure AI systems meet performance, scalability, observability, and security requirements.
• Mentor engineers and advocate for responsible AI practices, including PII/PHI and regulatory compliance.

Required Skills

• 10+ years of software engineering experience, with 3+ years in AI/ML or LLM-based application development.
• 2+ years of hands-on experience with LLM orchestration frameworks such as LangGraph, LangChain, or Semantic Kernel.
• 2+ years of experience building agentic AI systems or autonomous agents using OpenAI, Anthropic, or open-source LLMs.
• Strong proficiency in Python and FastAPI.
• Experience with vector databases like FAISS or Weaviate and RAG pipelines.
• Experience with cloud platforms (GCP preferred), microservices, and API-first development.
• Familiarity with CI/CD, DevOps, and observability tools for AI systems.
• Knowledge of building stateful, goal-driven agents capable of reasoning and planning.

Preferred Skills

• Experience with LLMOps, prompt engineering, and RAG optimization.
• Background in healthcare, HIPAA compliance, or regulated AI systems.
• Understanding of AI safety, alignment, and ethical AI design.

Key Skills

Education

Any Gradute