Lead AI Engineer (Scientific Multi Agent Systems)

TL;DR

Lead AI Engineer (Scientific Multi Agent Systems): Designing and building multi-agent systems that integrate scientific tools and computational workflows with an accent on agent evaluation frameworks and data engineering pipelines. Focus on developing MCP-compatible services and solving complex challenges in cheminformatics and drug discovery.

Location: Remote (USA, Canada, Europe or UK). Availability to work until at least 1:00 PM EST is required.

What you will do

• Design and build multi-agent systems integrating scientific tools, APIs, and cheminformatics libraries such as RDKit.
• Develop containerized deployment pipelines using Docker with observability via Langfuse and proper lifecycle management.
• Create agent evaluation frameworks, including automated testing, benchmarking, and performance monitoring.
• Build data preparation pipelines utilizing Snowflake, Airflow, DBT, PostgreSQL, and Oracle.
• Maintain code quality through CI/CD workflows, modular design practices, and technical documentation.

Requirements

• Strong Python software engineering skills.
• Experience with LLMs, tool-calling, and agent frameworks.
• Proven track record in developing multi-agent or workflow-oriented AI systems.
• Expertise in Docker and containerized application development.
• Ability to collaborate in a cross-functional scientific environment.
• Must be based in the USA, Canada, Europe, or UK and available until 1:00 PM EST.

Nice to have

• Experience with Langfuse, Snowflake Cortex, or Amazon Bedrock.
• AWS ECS/Fargate deployment experience.
• Proficiency in the data engineering stack: Snowflake, Airflow, DBT, Oracle.
• Experience in drug discovery and cheminformatics (RDKit, chemical structure analysis, assay data interpretation).

Culture & Benefits

• Competitive compensation.
• Flexible working hours.
• Continuous education, mentoring, and professional development programs.
• Collaboration with a team of high technical expertise.