Senior AI/ML Engineer — LLM Pipelines & Production

Google LLC; Austin (TX); On-site; USD 147,000 - 210,000; Full time

Benefits offered by this job

Health and welfare insurance

401(k) with company match

Paid time off (20 days/year)

Sick leave (40 hours/year)

Maternity leave (28–30 weeks)

Baby bonding leave

13 paid holidays

Job summary

Google LLC is seeking a software engineer to advance AI and LLM-driven systems across internal platforms and customer-facing products. You will build robust software components that productionalize AI prototypes and manage end-to-end pipelines, while collaborating with researchers and engineers.

The role emphasizes handling large-scale data, model integration, and delivering reliable services with strong testing and monitoring.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 2 years of experience with Large Language Models (LLMs) and Generative AI concepts (prompt engineering, RAG).
• 2 years of experience with software development in one or more programming languages, or 1 year with an advanced degree.

Responsibilities

• Write clean, testable production code in Python, C++, or Java for LLM pipelines and related systems.
• Deliver robust components and services that productionalize Data Science prototypes and AI workflows.
• Implement orchestration logic, context window management, parsing, and API integrations between LLMs and back-end/frontend systems.
• Build and maintain automated evaluation pipelines to monitor hallucinations, quality, and latency.
• Collaborate with Data Scientists, Web Solutions Engineers, and Technical Program Managers to clarify requirements and unblock delivery.

Skills

Python

C++

Java

LLM pipelines

Education

Bachelor's degree or equivalent practical experience

Job description

Google LLC is seeking a software engineer to advance AI and LLM-driven systems across internal platforms and customer-facing products. You will build robust software components that productionalize AI prototypes and manage end-to-end pipelines, while collaborating with researchers and engineers.

The role emphasizes handling large-scale data, model integration, and delivering reliable services with strong testing and monitoring.