| Location | Holladay, United States |
| Years of Experience | 2 years of experience |
| Commitment | FULL_TIME |
| Remote | See job post for details |
| First listed | In the last 2 days |
Job Description
Large Language Model (LLM) Systems Scientist
Research and develop multi-agent orchestration and decision-policy algorithms including inference time agent routing, task decomposition and coordination across both open weight and proprietary LLM and Transformer-based models using python, PyTorch and/or Tensorflow. Develop and scale vector-based retrieval and augmented generation (RAG) systems including vector index optimization, retrieval-latency tuning, hybrid (dense + sparse) search across SQL datastore, and embedding-pipeline throughput to support high-volume agentic reasoning across multiple AI applications. Research and develop novel training algorithms, including contrastive learning, using PyTorch and/or Tensorflow to specialize and align multi-agent LLM systems, and productionize them as platform-level training capabilities managed under Git-based version control and CI/CD. Design and scale the platform-level evaluation framework, including statistical benchmarking pipelines implemented using Python, pandas and numpy, automated regression suites, and quality and reliability dashboards, for evaluating LLM-driven generation and inference systems. Create graph-based knowledge representation and reasoning algorithms using graph neural networks (DGL) over semantic knowledge graphs supporting graph generation, node/edge inference, and graph-grounded retrieval for multi-agent LLM workflows. Develop the distributed multi-agent AI platform infrastructure on AWS that hosts production agent deployments serving multiple product lines, including the platform’s application pipelines developed in Swift. Research and implement safety and robustness methods for multi-agent LLM systems, including adversarial and prompt-injection robustness, data-exfiltration defenses, agent action sandboxing, and behavioral safety evaluation and red-teaming of agentic workflows operating against building protocol networks.
Requires: Master's Degree in Computer Science, 2 years of experience as an LLM Systems Scientist or AI Engineer, and proficiency with Python, PyTorch, TensorFlow, Numpy, Pandas, DGL, SQL, Git, AWS, Swift, LLM, Transformer-based systems, retrieval-augmented generation (RAG) and vector-based retrieval, and graph neural networks.
PassiveLogic number of job openings over time by month
ClimateTechList is the web's largest aggregator of climate, clean tech, renewable energy & green jobs. Contact us if you'd like to use partner or use our current or historical jobs data in any way.
Apply to Job
👉 Please mention that you found the job on ClimateTechList, this helps us get more climate tech companies listed here, thanks!
Get a referral to PassiveLogic
If possible, try to get a warm intro/referral to PassiveLogic before applying! Do a LinkedIn search to see who you may know at the company. See this LinkedIn post from Steven for more details on this tactic.
Join ClimateTechList Talent Collective
Want to be matched with companies directly? Apply to the talent collective.
Here's how it works:
You submit an application
We'll share your profile with climate tech companies potentially interested in chatting with you
We'll reach out if there's a company interested in talking to you.
No spam. Unsubscribe any time.
Join ClimateTechList Talent Collective
Want to be matched with companies directly? Apply to the talent collective.
Here's how it works:
You submit an application
We'll share your profile with climate tech companies potentially interested in chatting with you
We'll reach out if there's a company interested in talking to you.