Senior Software Engineer - Integrations - AI/ML
Senior engineer owning production Python connectors and AI/ML integrations for ClickHouse, including vector search, RAG, feature pipelines, and LLM applications. Requires 7+ years of development experience and hands-on Data Science or ML Engineering experience.
About the job
Responsibilities
- Own and evolve ClickHouse’s Python connector and SDK ecosystem, improving performance, reliability, and API design.
- Design AI/LLM integrations and patterns for retrieval-augmented generation, ML feature pipelines, and LLM-powered data applications.
- Own the architecture, performance, and feature direction of integrations across the AI and LLM ecosystem, including LangChain, LlamaIndex, n8n, embedding pipelines, vector stores, and feature stores.
- Engage with the open-source community by triaging issues, supporting contributors, advocating for users, and shaping the roadmap from real-world feedback.
- Collaborate with Product, Cloud, and engineering teams on integration priorities.
- Apply practitioner insight from Data Engineering and Data Science workflows to roadmap decisions.
Requirements
- 7+ years of software development experience, including hands-on experience as a Data Scientist or ML Engineer.
- Proven experience designing, building, and maintaining production-grade Python connectors, SDKs, or integrations for a major platform.
- Production experience with AI/ML data-engineering workflows, including embedding generation, vector search, feature pipelines, or LLM-powered tooling.
- Strong experience with the Python data ecosystem, including Pandas, NumPy, and Pydantic.
- Strong database fundamentals, including SQL, data modeling, query optimization, and OLAP or analytical databases.
- Experience with concurrent Python, including threading, multiprocessing, and asynchronous patterns.
- Excellent written and verbal communication skills, including collaboration across engineering teams and open-source communities.
Nice-to-haves
- Experience as a Data Engineer or Data Scientist in a product-facing or platform role.
- Familiarity with ClickHouse or similar high-performance OLAP platforms.
- Familiarity with the JVM ecosystem.
- Experience deploying AI/ML models in production, including inference APIs and vector databases.
- Familiarity with dbt, Airflow, Dagster, or Prefect.
Compensation and Benefits
- Equity through company stock options.
- Healthcare contributions.
- Flexible time off in the United States and generous entitlement in other countries.
- USD $500 home-office setup allowance for remote employees.
- Opportunities to participate in company-wide global gatherings.
Skills
Python, Python Sdks, pandas, NumPy, Pydantic, SQL, Data Modeling, Query Optimization, Olap Databases, Concurrency, Threading, Multiprocessing, Async Programming, LangChain, Llamaindex
Similar jobs
Fullstack Engineering jobs
Benchling
San Francisco, CA
Founding engineer responsible for the architecture, development, and operation of Benchling’s internal tooling and automation systems. The role requires 7+ years of production software engineering experience, strong integration and security fundamentals, and hands-on technical leadership.
Commure
Mountain View, CABuild and ship full-stack features for high-volume healthcare billing workflows, including claims, appointments, and payments. The role requires 5+ years of production experience, strong frontend and API skills, and the ability to design reliable, observable systems.
Flaglerhealth
United States
Senior fullstack engineer responsible for building and supporting a contract-first clinical operations platform across Vue, TypeScript, Node.js, and MongoDB. Requires 5+ years of web application experience and 3+ years in healthcare revenue cycle management.
Plenful
San Francisco, CA
Senior Software Engineer building and scaling a healthcare workflow automation platform. Own core infrastructure for orchestration, integrations, and data pipelines processing millions of tasks monthly in serverless and containerized environments. Requires 7+ years experience with distributed systems, databases, and large-scale pipelines.
Shield AI
San Diego, CABuild and operate reusable full-stack applications, backend services, SDKs, and APIs for shared product capabilities. The role requires at least four years of software engineering experience, strong systems thinking, and ownership of secure production software.