About the role

Software Engineer applying backend expertise in Data, Retrieval, and AI Agents at BenchSci. Contributing to search and retrieval infrastructure and evolving data models in scientific research.

Responsibilities

Utilize the Agent Development Kit (ADK) to design, develop, and deploy autonomous agents and "skills" capable of multi-step data retrieval tasks.
Design and develop backend systems and APIs that expose bioinformatics data to power application roadmaps.
Implement advanced search and retrieval mechanisms (RAG), to provide (LLMs) with up-to-date grounded information, tune storage technologies and create high-performance query plans.
Design solutions and adapt existing approaches to resolve issues, contributing to web app architecture and interfaces.
Operationalize production-grade data pipelines using processing engines like Apache Beam to move data from research to platform efficiently .
Collaborate with other engineers to solve document extraction, enrichment, retrieval challenges, capturing and modeling scientific experiments from unstructured sources.
Perform troubleshooting analysis and resolution for production issues in a timely manner, ensuring code is testable, self-documenting, and reliable.
Communicate cross-cutting decisions to all potentially impacted teams.
Work on client-facing projects involving some of the largest Pharmaceutical companies in the world
Balance working independently on core tasks while proactively identifying when collaboration or help is needed for high-complexity architectural shifts.

2+ years of experience working as a professional software developer.
Advanced understanding of Python and experience developing robust API solutions.
Hands-on experience or deep technical interest in the Agent Development Kit (ADK) or similar frameworks.
Proficiency in SQL; strong understanding distributed systems, data structures, algorithms, and indexing strategies for large-scale data storage
Experience with cloud reference architectures and developing specialized stacks on cloud services
Demonstrated ability to apply coding patterns and follow established team processes with minimal guidance.
Familiarity with GCP or similar cloud technologies including data engineering tools (i.e Dataflow, BigQuery, AlloyDB, Spanner, Pub/Sub, Looker... etc.)
Strong cross-team collaboration skills with the ability to explain relevant areas of the codebase to others.
Familiarity with Infrastructure as Code(IaC) is nice to have.