Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an AI engineer with 10+ years building production ML and large language model systems across Cohere, Google, Scale AI, and Tempus. I focus on systems embedded in real workflows—retrieval, agentic decisioning, and evaluation—where correctness, latency, and traceability directly impact outcomes. I take end-to-end ownership from data pipelines to production behavior, collaborating across data engineering, ML, and product teams to deliver robust, scalable AI solutions.…I am an AI engineer with 10+ years building production ML and large language model systems across Cohere, Google, Scale AI, and Tempus. I focus on systems embedded in real workflows—retrieval, agentic decisioning, and evaluation—where correctness, latency, and traceability directly impact outcomes. I take end-to-end ownership from data pipelines to production behavior, collaborating across data engineering, ML, and product teams to deliver robust, scalable AI solutions.

Chase Bradley Sta

AI Engineer, Data Scientist, Full Stack Developer, +2





I am an AI engineer with 10+ years building production ML and large language model systems across Cohere, Google, Scale AI, and Tempus. I focus on systems embedded in real workflows—retrieval, agentic decisioning, and evaluation—where correctness, latency, and traceability directly impact outcomes. I take end-to-end ownership from data pipelines to production behavior, collaborating across data engineering, ML, and product teams to deliver robust, scalable AI solutions.…I am an AI engineer with 10+ years building production ML and large language model systems across Cohere, Google, Scale AI, and Tempus. I focus on systems embedded in real workflows—retrieval, agentic decisioning, and evaluation—where correctness, latency, and traceability directly impact outcomes. I take end-to-end ownership from data pipelines to production behavior, collaborating across data engineering, ML, and product teams to deliver robust, scalable AI solutions.

Available to hire

I am an AI engineer with 10+ years building production ML and large language model systems across Cohere, Google, Scale AI, and Tempus. I focus on systems embedded in real workflows—retrieval, agentic decisioning, and evaluation—where correctness, latency, and traceability directly impact outcomes.

I take end-to-end ownership from data pipelines to production behavior, collaborating across data engineering, ML, and product teams to deliver robust, scalable AI solutions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

English

Fluent

Work Experience

Staff AI Engineer at Cohere

April 1, 2023 - Present

Built production retrieval layer using Embed v3 + Rerank across multi-million document corpora; designed hybrid retrieval architecture (BM25 + dense embeddings + query rewriting); implemented tool-selection layer and multi-agent coordination; built evaluation systems; optimized performance and latency across multi-step workflows.

Senior AI Engineer at Scale AI

January 1, 2022 - March 1, 2023

Built large-scale data debugging and curation workflows; designed data-centric iteration loops; developed document understanding systems with PDF layouts and OCR artifacts; built multi-stage processing pipelines and deterministic extraction workflows; defined evaluation frameworks mapping model failures back to data issues.

Senior AI Engineer at Tempus

April 1, 2020 - December 1, 2021

Built query and data access layers for Tempus Lens; designed ingestion/normalization pipelines for heterogeneous clinical data; supported decision workflows in the TIME Trial Program; ensured models operated on clean, normalized inputs.

Senior Software Engineer at Google Cloud AI Platform

January 1, 2019 - March 1, 2020

Built ML infrastructure and backend services for scalable training, evaluation, and deployment; designed systems managing model lifecycle; improved observability; optimized distributed data processing and inference pipelines.

Software Engineer II at Google

January 1, 2017 - December 1, 2018

Built distributed data processing pipelines (Beam/MapReduce); contributed to data-to-model workflows with BigQuery ML; integrated ML models into production services with safe rollout, monitoring, and rollback; built backend services for high throughput with strict latency requirements.

Software Engineer at Google

January 1, 2016 - December 1, 2016

Built backend data ingestion and preprocessing pipelines for early ML platform capabilities including AutoML; focused on distributed systems fundamentals and reliability improvements.