AI Software Engineer (KBase Project)

Lawrence Berkeley National Laboratory
Berkeley, CA, United States
12 days ago
Apply on diversityjobs.com
Prepare application

Role details

Contract type
Temporary to permanent
Employment type
Full-time (> 32 hours)
Compensation
$117,132.0 - $146,400.0
Working hours
Regular working hours

Tech stack

Agile Methodology Artificial Intelligence Data Analysis Computational Biology Information Engineering Data Stores Github Python (Programming Language) Metadata Standards Open Source Technology Tensorflow Software Engineering
+10 more
Systems Integration Pytorch Large Language Models Prompt Engineering Data Lakes Pyspark Scikit Learn Information Technology Virtual Agents Software Library

Job description

  • Build agent-based tools using Python, LangChain, LangGraph, CrewAI, and modern LLMs.
  • Develop AI agents that interact with the KBase Datastore and Delta Lake/PySpark Lakehouse.
  • Design agent state management, prompt strategies, and benchmarking to ensure reliability and performance.
  • Develop robust, tested software for agent orchestration and workflow integration.
  • Collaborate with the AI/ML team on foundational models and tools for microbial genomics.
  • Integrate AI capabilities across front-end and back-end systems.
  • Develop, test, maintain, and document software following team quality standards.
  • Provide technical guidance and mentorship on AI tools and system integration.

What We Are Looking For

Requirements

  • A Bachelor’s Degree (or equivalent knowledge/training) in Computer Science, Engineering, Computational Biology, or a related field and a minimum of 5 years of relevant work experience in AI agent frameworks, data engineering, and software development in service of scientific research or an equivalent combination of education and experience.
  • Experience designing and implementing intelligent agents for scientific or technical workflows for analyzing biology and environmental data sets.
  • Experience working with large language models (LLMs) and prompt engineering across multiple providers.
  • Demonstrated experience with PySpark and data engineering using modern lakehouse architectures, including Delta Lake.
  • Experience deploying and supporting data- and compute-intensive workflows on high-performance computing (HPC) systems and/or cloud-based research infrastructure.
  • Demonstrated proficiency in Python and AI agent frameworks, including LangChain, LangGraph, and CrewAI.
  • Familiarity with machine learning libraries, such as PyTorch, TensorFlow, and Scikit-learn.
  • Knowledge of open-source collaboration, including GitHub workflows and Agile practices.
  • Strong understanding of AI agent architecture, including agent state management, evaluation, and benchmarking.
  • Demonstrated analytical and problem-solving skills, including the ability to identify, troubleshoot, and resolve technical problems of diverse scope where analysis of data requires evaluation of identifiable factors.
  • Excellent oral and written communication skills, including the ability to organize and present technical information effectively to both technical and non-technical audiences.
  • Demonstrated interpersonal and collaboration skills, including the ability to work effectively with a variety of scientific, operations, and technical teams., * A Master’s Degree (or equivalent knowledge/training) in Computer Science, Engineering, Computational Biology, or a related field and a minimum of 3 years of relevant work experience in AI agent frameworks, data engineering, and software development in service of scientific research or an equivalent combination of education and experience.
  • Experience with scientific reproducibility practices and metadata standards.
  • Familiarity with scientific data analysis and visualization techniques., * Appointment Type: This is a full time, exempt from overtime pay (monthly paid), 1 year (benefits eligible), Term appointment with the possibility of extension or conversion to Career appointment based upon satisfactory job performance, continuing availability of funds and ongoing operational needs.

Benefits & conditions

  • Salary Information: This position has a budgeted salary range of $117,132 - $146,400 annually, for job code C70.2. It is not typical for an individual to be offered a salary at or near the top of the budgeted range for a position. Salary for this position will be commensurate with the final candidate’s qualification and experience, including skills, knowledge, relevant education, certifications, and aligned with the internal peer group.
  • Background Check: This position is subject to a background check. Any convictions will be evaluated to determine if they directly relate to the responsibilities and requirements of the position. Having a conviction history will not automatically disqualify an applicant from being considered for employment.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on diversityjobs.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

6:36 min

Funding open source through GitHub Accelerator and Sponsors

Stormy Peters · World Congress 2023

4:32 min

Harnessing Spark with Python using PySpark and Py4J

Ayon Roy · LIVE

2:35 min

Preventing remote code execution in PyTorch models

Balázs Kiss · World Congress 2023

2:14 min

Exploring internal AI product initiatives and global engineering roles

Maria Apazoglou · Coffee With Developers

2:40 min

Using GitHub primitives for internal documentation and corporate operations

Kyle Daigle · Coffee With Developers

4:29 min

Implementing AI assistants for workplace productivity

Markus Hacker Markus Hacker +1 · World Congress 2025

Videos

See all

Related articles

See all