Lead AI Agentic Solutions Engineer

Confiz Limited; Seattle, Northern (WA, KY); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Confiz Limited in Seattle, WA seeks an experienced AI Agentic Solutions Engineer to lead the design and delivery of scalable agentic systems. You will own end-to-end architecture across orchestration, retrieval, and memory management, partnering with product, security, and infra teams.

The role emphasizes hands-on development with LLMs, prompt engineering, and cost-aware decisions, plus mentoring junior engineers and shaping engineering standards while collaborating with stakeholders.

Qualifications

• 6+ years of professional software engineering experience designing scalable distributed systems.
• Hands-on experience with LLMs, foundation model APIs (OpenAI, Anthropic, Google, etc.), prompt engineering, retrieval‑augmented generation (RAG) architectures, and embedding‑based search in production environments.
• Experience designing, building, and operating AI agents or agentic workflows in production, including tool‑use, orchestration, and integration with downstream systems.
• Strong understanding of how to assemble, prune, and structure context for agents to maximize decision quality within token, latency, and cost constraints.
• Experience designing evaluation frameworks and safety guardrails for LLM‑based systems, including offline benchmarks, online telemetry, and responsible deployment practices.
• Familiarity with short‑term and long‑term memory patterns for agents, vector stores, conversation state, and durable workflow state.
• Hands‑on experience with agentic frameworks such as Claude Agent SDK, LangGraph, AutoGen, CrewAI, Semantic Kernel, or OpenAI Assistants API.
• Familiarity with multi‑agent orchestration patterns: task decomposition, tool‑use pipelines, and human‑in‑the‑loop workflows.
• A product‑minded approach to engineering: strong instincts for user impact, comfortable pushing back on requirements when the right solution isn’t the one initially asked for, and able to translate business intent into agentic capabilities.
• Proficiency in Python; strong grasp of multiple tech stacks and cloud‑native development on AWS and/or GCP.
• Experience working with cross‑functional teams including product, business, infrastructure, and security stakeholders.
• Strong verbal and written communication skills; ability to articulate complex technical decisions to both technical and non‑technical audiences.
• Agile development experience (Scrum, Kanban, Lean, or similar) with a continuous improvement and quality mindset.
• Bachelor’s or Master’s degree in Computer Science, Engineering, or equivalent practical experience.

Responsibilities

• Define agentic solutions end-to-end with measurable outcomes.
• Design and build core agentic solutions across orchestration, tool‑use pipelines, and integration with enterprise systems.
• Own end-to-end solution design for agentic solutions spanning multiple engineers’ work, with full upstream/downstream integration consideration.
• Apply context engineering to determine what an agent sees, when, and why — balancing token economics, latency, and decision quality across RAG patterns, structured retrieval, and dynamic prompt assembly.
• Develop and own evaluations and guardrails that demonstrate solutions are safe, reliable, and accurate — offline benchmarks, online production telemetry, and failure-mode analysis.
• Architect memory and state management approaches that let agents reason across sessions, users, and workflows — short‑term context, long‑term memory, and durable conversation state.
• Apply AI fluency to integrate LLM APIs, embedding models, vector stores, and agentic frameworks into production services; evaluate and adopt emerging techniques as appropriate.
• Make and clearly articulate technical trade-offs between short‑term delivery needs and long‑term scalability, factoring in design, framework choice, model selection, and infrastructure costs.
• Design systems accounting for current and upcoming product cycles, team‑level cost responsibility, and alignment with cross‑functional roadmaps.
• Lead design and code reviews across the team; provide actionable feedback and maintain a high bar for quality, testability, and extensibility.
• Design key metrics, evaluations, and observability patterns for agentic solutions; drive accountability for performance, cost, accuracy, and security of feature work.
• Work with business, infrastructure, and security teams to deliver enhancements, reliability improvements, and bug fixes for production AI systems.
• Surface potential design or delivery conflicts in the current or upcoming product cycle and make clear recommendations on the best path forward.
• Mentor and support junior engineers across a wide spectrum of technical activities; participate in hiring interviews with clear, specific feedback.
• Ensure own work and team members’ work follows Confiz’s engineering and security standards; contribute to those standards

Skills

Python

LLM APIs

Agentic frameworks

System design

Observability

Cross-functional collaboration

Education

Bachelor’s or Master’s degree in Computer Science or Engineering

Tools

Claude Agent SDK

LangGraph

AutoGen

CrewAI

Semantic Kernel

OpenAI Assistants API

Job description

Confiz Limited in Seattle, WA seeks an experienced AI Agentic Solutions Engineer to lead the design and delivery of scalable agentic systems. You will own end-to-end architecture across orchestration, retrieval, and memory management, partnering with product, security, and infra teams.

The role emphasizes hands-on development with LLMs, prompt engineering, and cost-aware decisions, plus mentoring junior engineers and shaping engineering standards while collaborating with stakeholders.