Senior AI Agent & LLM Architect

GenixBit Labs Pvt. Ltd.; San Francisco (CA); Híbrido; USD 185 000 - 245 000; Tempo integral

Resumo da oferta

Genixbit in San Francisco is seeking a Senior AI Agent & LLM Architect for a full-time, hybrid role. You will design production-grade multi-agent cognitive networks, RAG memory pipelines, and autonomous reasoning loops to automate enterprise processes.

You will architect resilient orchestration, optimize vector indexing and retrieval, deploy open-source LLMs on AWS GPUs, and evaluate latency, safety guardrails, and accuracy to ensure robust performance.

Qualificações

• 5+ years of AI engineering, NLP, or distributed systems work.
• Proven ability to ship autonomous multi-agent networks in production.
• Strong fundamentals in AI architectures and systems.

Responsabilidades

• Architect resilient multi-agent orchestration frameworks using LangGraph, CrewAI, and AutoGen
• Optimize vector indexing, context-window retrieval, and prompt guardrails
• Deploy open-source LLMs (Llama 3, Mistral, Qwen) with vLLM on AWS GPU clusters
• Conduct system evaluations for latency, safety guardrails, and accuracy

Conhecimentos

AI engineering

NLP

distributed systems

Ferramentas

Python

PyTorch

LangChain/LangGraph

Pinecone

Qdrant

Descrição da oferta de emprego

Senior AI Agent & LLM Architect

Full-time San Francisco USA Hybrid Senior $185,000 - $245,000 / year Closes: Nov 18, 2026

About the Role

Design and deploy production-grade multi-agent cognitive networks, RAG memory pipelines, and autonomous reasoning loops for enterprise automation.

Key Responsibilities

• Architect resilient multi-agent orchestration frameworks using LangGraph, CrewAI, and AutoGen
• Optimize vector indexing, context-window retrieval, and prompt guardrails
• Deploy open-source LLMs (Llama 3, Mistral, Qwen) with vLLM on AWS GPU clusters
• Conduct system evaluations for latency, safety guardrails, and accuracy

Requirements

• 5+ years in AI engineering, NLP, or distributed systems development
• Hands-on mastery of Python, PyTorch, LangChain/LangGraph, and Pinecone/Qdrant
• Proven track record of shipping autonomous multi-agent networks in production
• Strong expertise in vector embeddings and enterprise API integration

Python PyTorch LangGraph Pinecone FastAPI AWS