Senior AI Engineer - Model Selection and Orchestration
New
Z
ZipFintech AI
US-based employeesFull-TimeSenior
Salary$162,000 - $205,000 annual base pay range
Apply NowOpens the employer's application page
Job Details
- Experience
- Minimum of 10 years of related experience with a Bachelor's degree; or 6 years and a Master's degree; or a PhD with 3 years experience; or equivalent experience.
- Required Skills
- PythonCloud ComputingMachine LearningTypeScriptCI/CDLLM
Requirements
- Minimum 10 years of related experience with a Bachelor's, 6 years with a Master's, or 3 years with a PhD, or equivalent professional experience.
- 10+ years of professional experience building, testing, and operating production software.
- Proven track record delivering AI or ML-enabled applications beyond the prototype stage.
- Strong experience with Python or TypeScript.
- Practical experience with LLM tool calling, structured outputs, retrieval-augmented generation (RAG), and agent orchestration.
- Strong understanding of API design, automated testing, and distributed services.
- Experience with cloud deployment, CI/CD, observability, and secrets management.
- Ability to evaluate classification quality, system uncertainty, and fallback strategies.
- Experience implementing idempotency, retry strategies, and failure recovery in production environments.
- Strong judgment on when to use deterministic software versus AI models.
Responsibilities
- Design and implement decision layers that determine how agents respond to tasks, choosing between deterministic logic, retrieval, models, or human escalation.
- Develop intent classification and clarification capabilities to identify ambiguous requests and determine when additional information is required.
- Benchmark and select models based on quality, latency, safety, and inference costs.
- Implement robust model orchestration including routing, structured outputs, retries, and fallback strategies.
- Integrate agents with APIs and tools while ensuring secure authentication, authorization, and policy enforcement.
- Partner with Security and Risk teams to implement input/output protections and data handling safeguards.
- Develop reusable orchestration patterns and model adapters for use by internal engineering teams.
- Monitor system behavior, investigate production failures, and iteratively improve model selection and orchestration.
View Full Description & ApplyYou'll be redirected to the employer's site
