Applied AI Agent Engineer for Production-Ready AI

Sapienceai; Seattle, Northern (WA, KY); Hybrid; USD 204,000 - 216,000; Full time

Benefits offered by this job

Generous health benefits

Job summary

Sapience AI in Seattle is seeking an experienced Applied AI Engineer to turn models into dependable, production-ready behavior. You will design agentic systems, grounding, reasoning, and tool use to help MINERVA understand requests and take reliable actions.

You will work at the intersection of product and AI stack, balancing latency, cost, safety, and trust with a focus on real-world deployment and measurable impact across professional communities.

Qualifications

• Five or more years in software engineering with applied AI/ML.
• Hands-on experience building agentic systems or retrieval-augmented apps in production.
• Strong grounding, tool use, and understanding model limits.
• Experience making AI behavior safe, reliable, and observable.
• Strong Python and solid software engineering fundamentals.
• Rigor about evaluation and honest handling of uncertainty.
• Care for member trust and safety.

Responsibilities

• Own seven areas of responsibility across applied AI.
• Design and build the agents that understand requests, reason, and act.
• Grounding and retrieval aligned to the KO graph and COGENT architecture.
• Integrate neural and symbolic reasoning into applied behavior.
• Build tools and actions with safe access to systems and data.
• Create guardrails to keep agent behavior safe and within bounds.
• Evaluate and instrument AI behavior in production.
• Productionize AI with focus on latency, cost, and reliability.

Skills

Software engineering

Applied AI/ML

Agentic systems

Python

Evaluation & uncertainty

Trust & safety

Tools

LLM frameworks

Orchestration tooling

Vector databases

Graph access

Python

TypeScript

Cloud platforms

Containers

Job description

Sapience AI in Seattle is seeking an experienced Applied AI Engineer to turn models into dependable, production-ready behavior. You will design agentic systems, grounding, reasoning, and tool use to help MINERVA understand requests and take reliable actions.

You will work at the intersection of product and AI stack, balancing latency, cost, safety, and trust with a focus on real-world deployment and measurable impact across professional communities.