AI Agent Architect for Edge-Ready LLM Systems

Bosch USA

Sunnyvale (CA)

On-site

USD 165,000 - 180,000

Full time

11 days ago

Application generator

Don’t send a generic resume — generate a resume and cover letter tailored to this exact role.

Get past ATS filters

Benefits offered by this job

Health coverage

401(k) with matching

Paid time off

Parental leave

Life & disability protection

Long-term incentive

Job summary

Bosch USA in Sunnyvale, California, is hiring for an AI Research Engineer focused on foundation models, Gen AI, and trustworthy AI for ADAS and Industry AI. You will design and implement agentic systems, evaluate robust memory architectures, and enable edge deployment.

A strong background in Python, LLMs, and research is essential, with opportunities for impact across Bosch product lines. The role emphasizes rigorous experimentation, reproducible results, and collaboration with academia and

Qualifications

Bachelor or master’s degree in computer science or engineering.
Strong Python programming skills and hands-on experience with LLMs and agentic systems.
Experience designing experiments, ablations, statistics, and measurable KPIs.
Excellent written and verbal communication and ability to present reproducible results.
Familiarity with prompting, evaluation, and error analysis in ML workflows.
Ability to plan, execute, and document complex AI research studies.

Responsibilities

Design, build, and evaluate agentic AI systems that can plan, reason, act, and collaborate across tools and environments.
Develop robust agent harnesses and evaluation frameworks covering end-to-end testing and metrics for success, cost, latency, robustness, and safety.
Implement self-improving agent loops using reflection, critique, self-debugging, and iterative optimization strategies driven by agent experience.
Architect and optimize agent memory systems, including short-term and long-term memory, retrieval-augmented generation, summarization, compression, forgetting policies, and privacy-aware retention.
Enable reliable deployment of agents on constrained and edge environments, focusing on model/runtime optimization, partial or offline execution, secure tool-use, and edge-cloud coordination.