Software Engineer III, Agent Quality and Efficiency Optimization

Brak informacji o wynagrodzeniu

MidOn-site·WarszawaFull-time

#462413·Dodano 2 dni temu·2

Źródło: Google

Aplikuj teraz

Tech Stack / Keywords

Agent Development KitVertex AILLMs LangGraph LangChain Go C++Python machine learning

Podsumowanie oferty

Build agent optimization systems for the Google Cloud AI Research team across the Agent Development Kit and Vertex AI serving stack. Measure agent quality, cost, and latency, and develop optimization techniques for enterprise workloads.

Wymagania

Bachelor's degree or equivalent practical experience.
2 years of software development experience in one or more programming languages such as Go, C++, or Python, or 1 year of experience with an advanced degree.
2 years of experience with machine learning, large language models (LLMs), or applied AI.

Nice to have:

Master's degree or PhD in Computer Science, Machine Learning, or a related technical field.
Experience building, deploying, or optimizing LLM applications or agentic frameworks such as Agent Development Kit, LangGraph, or LangChain.
Experience with model serving optimization, inference caching, model routing, or LLM cost and latency profiling.
Experience instrumenting, benchmarking, or evaluating ML systems in production.
Experience with technical leadership, mentoring engineers, or driving cross-team engineering initiatives.

Obowiązki

Design, build, and ship agent optimization systems that turn insights from evaluation results and production traces into persistent improvements, including skills, prompt and tool tuning recipes, task-level cost and quality telemetry, model routing, and durable and deferred execution across the Agent Development Kit and Vertex AI serving stack.
Measure quality, cost, and latency per task and use the data to drive engineering work.
Shape the team's optimization roadmap and help set technical direction for improving enterprise agents' quality and cost over time.
Build benchmark optimization techniques for open-source benchmarks and first-party and enterprise agent workloads to demonstrate quality and efficiency improvements.

Benefity

15% bonus target.
Equity.

Premie

Udziały pracownicze

Inne informacje

In most instances, the hiring process requires in-person interviews.

Google

113 aktywnych ofert

Zobacz wszystkie oferty

Aplikuj teraz