We are building a Lead AI Engineer, Open Telemetry Observability role to deliver reliable observability across distributed and multi‑agent AI systems at scale. You will apply Python engineering and GenAI expertise to ship well‑instrumented AI platforms, covering packaging and binarizing. Join the team to strengthen tracing, evaluation, and operability.
Responsibilities
- Design and deliver Open Telemetry Observability capabilities for distributed tracing and multi‑agent systems
- Build, package and binarize Python applications to support core software engineering needs
- Integrate GenAI technologies with agentic development frameworks to enable agentic solutions
- Execute agentic evaluations to validate performance and reliability of AI systems
- Implement distributed processing workflows using frameworks such as Ray and Kubernetes
- Collaborate with cross‑functional teams to ship observable and maintainable AI solutions
- Optimize multi‑agent observability pipelines to improve scalability and accuracy
Requirements
- Proven track record with 5+ years of core software engineering in Python, including development, packaging and binarizing
- Deep implementation experience in Open Telemetry Observability for distributed tracing and multi‑agent observability
- Advanced expertise in GenAI technologies and agentic development frameworks
- Solid background in agentic evaluations
- Hands‑on experience with distributed processing frameworks such as Ray and Kubernetes
- English proficiency at B2 level (Upper‑Intermediate) or higher
