Senior AI Engineer, Agentic Systems and MCP

Findjobit; United States; Remote; USD 150,000 - 190,000; Full time

Benefits offered by this job

100% remote

Long-term contract

Job summary

Niuro is hiring a Senior AI Engineer for an AI-native company building agentic workflows and large-scale document intelligence for regulated industries. You will design multi-agent systems, MCP integrations and the evaluation pipelines that keep them reliable.

Lead the design and orchestration of production ML/AI workflows, evaluate open-weight models, and contribute to document intelligence pipelines across OCR, classification and NER in a fully remote, long-term contract setting.

Qualifications

• 6+ years in software engineering, shipping production ML/AI systems.
• Deep Python proficiency.
• Hands-on orchestration of coding agents in real workflows.
• Strong knowledge of MCP, tool calls and agent-to-agent protocols.
• LLM evaluation pipelines in production.
• Open-weight models (Qwen, Llama, Mistral), MoE, and platforms like AWS Bedrock, Vertex AI or Azure OpenAI.
• C1 English.

Responsibilities

• Design and orchestrate multi-agent workflows: planning, implementation and validation agents.
• Architect MCP integrations and modularize async, heavy workloads.
• Run spec-driven and eval-driven development with constraint files that prevent agent drift.
• Build LLM evaluation pipelines: golden datasets, LLM-as-judge, precision and recall tracking.
• Evaluate, fine-tune and deploy open-weight models across hosting providers.
• Contribute to document intelligence pipelines: OCR, classification and NER.

Skills

Python

Agent orchestration

MCP

LLM evaluation

Open-weight models

English (C1)

Tools

Claude Code

Codex

AWS Bedrock

Vertex AI

Azure OpenAI

Job description

Niuro is hiring a Senior AI Engineer for an AI-native company building agentic workflows and large-scale document intelligence for regulated industries. You will design multi-agent systems, MCP integrations and the evaluation pipelines that keep them reliable.

What you will do

• Design and orchestrate multi-agent workflows: planning, implementation and validation agents.
• Architect MCP integrations and modularize async, heavy workloads.
• Run spec-driven and eval-driven development with constraint files that prevent agent drift.
• Build LLM evaluation pipelines: golden datasets, LLM-as-judge, precision and recall tracking.
• Evaluate, fine-tune and deploy open-weight models across hosting providers.
• Contribute to document intelligence pipelines: OCR, classification and NER.

What you bring

• 6+ years in software engineering, shipping production ML/AI systems.
• Deep Python proficiency.
• Hands-on orchestration of coding agents (Claude Code, Codex) in real workflows.
• Strong knowledge of MCP, tool calls and agent-to-agent protocols.
• LLM evaluation pipelines in production.
• Open-weight models (Qwen, Llama, Mistral), MoE, and platforms like AWS Bedrock, Vertex AI or Azure OpenAI.
• C1 English.

Nice to have:

OCR, OpenCV, AWS Textract, SageMaker; Spanish, Portuguese or Japanese.

100% remote, long-term contract with Niuro.