Production AI Engineer — Client-Facing, RAG & LLM (Hybrid)

Elios AI; Seattle (WA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Elios AI in Seattle, WA seeks a senior software engineer to build production AI systems for enterprise clients. You will own and ship LLM-powered features, including RAG workflows, with strong emphasis on observability, cost control, and measurable real-world impact.

You'll work hands-on across Python, TypeScript, React, and modern backends, collaborating directly with clients to translate technical decisions into clear outcomes while staying current with evolving AI tooling.

Qualifications

• 5+ years of production software engineering with hands-on LLM-focused work.
• Experience shipping AI systems that real users depend on with measurable outcomes.
• Proficiency across Python, TypeScript, React, and modern backend frameworks.
• Client-facing or consulting delivery experience with a track record of shipped projects.
• Hands-on builder mindset; able to own and deliver end-to-end.

Responsibilities

• Build and ship LLM-powered features into production, including RAG pipelines and model integrations.
• Instrument systems with evals, observability, latency optimization, and cost management.
• Work directly with client stakeholders, translating technical decisions for non-technical audiences.
• Own your workstream from scoping through deployment.
• Use modern AI tooling to amplify output while owning every line that ships.
• Stay current with frameworks, protocols, and models as tooling evolves.

Skills

LLM-focused development

Full-stack Python/TS/React

Client-facing delivery

Production AI systems

Observability and cost management

Job description

Elios AI in Seattle, WA seeks a senior software engineer to build production AI systems for enterprise clients. You will own and ship LLM-powered features, including RAG workflows, with strong emphasis on observability, cost control, and measurable real-world impact.

You'll work hands-on across Python, TypeScript, React, and modern backends, collaborating directly with clients to translate technical decisions into clear outcomes while staying current with evolving AI tooling.