Senior AI/ML Engineer — Production AI Pipelines (SF)

True; San Francisco (CA); On-site; USD 180,000 - 275,000; Full time

Job summary

N/A is seeking an experienced AI/ML engineer to build and operate the systems layer for an enterprise process intelligence platform in San Francisco. You will ship reliable AI features, measure quality, and improve product behavior using hosted frontier models and real customer data.

You will design and maintain Python services, integrate with LLM APIs, implement retrieval and context construction, and craft guardrails and benchmarks. Visa sponsorship is available for this on-site role.

Qualifications

• 4 to 10 years of applied AI or ML engineering experience, including shipping and maintaining production systems for external customers.
• Strong Python skills, experience with Go, asynchronous services, and AI/ML tooling.
• Hands-on experience with hosted LLM APIs, RAG or retrieval, structured outputs, tool use, or multi-step agent workflows.
• Experience building AI evaluations or benchmarks and improving system quality through testing, monitoring, and customer feedback.
• Production software engineering experience across the AI lifecycle, from data and context preparation to user-facing product behavior.
• Strong systems thinking, ownership, and communication skills, with experience building products in a startup or similarly fast-moving environment.
• A bachelor's degree or higher in computer science, engineering, or a related technical field.

Responsibilities

• Build and operate Python services and AI pipelines, including retrieval, context construction, structured extraction, orchestration, and model or provider selection.
• Develop evaluation datasets, benchmarks, regression tests, guardrails, and fallback paths to measure and improve AI quality.
• Monitor production systems and address latency, cost, reliability, and failure handling.
• Trace end-to-end data flows from raw enterprise sources to generated outputs and user-facing product behavior.
• Use customer feedback and observed product performance to iterate on features and ship improvements.
• Make pragmatic decisions about architecture, technical debt, and when to build or adopt existing tools.

Skills

Python

Go

Asynchronous services

AI/ML tooling

Retrieval / RAG

Production software engineering

Education

Bachelor's degree in CS/engineering

Tools

Hosted LLM APIs

Benchmarks

Monitoring tools

Job description

N/A is seeking an experienced AI/ML engineer to build and operate the systems layer for an enterprise process intelligence platform in San Francisco. You will ship reliable AI features, measure quality, and improve product behavior using hosted frontier models and real customer data.

You will design and maintain Python services, integrate with LLM APIs, implement retrieval and context construction, and craft guardrails and benchmarks. Visa sponsorship is available for this on-site role.