3 months ago
Remote, CanadaSenior
Responsibilities
- Lead the design and development of next-generation AI agents and Agentic Assist systems.
- Define system architecture, core modeling approaches, and multi-step agent workflows.
- Design, deploy, and optimize LLM-powered systems, including RAG pipelines, multi-agent orchestration, and domain-adapted models.
- Improve reasoning, planning, and tool-use capabilities in production AI applications.
- Develop offline benchmarks, online experiments, and LLM-as-a-judge evaluation strategies.
- Diagnose and mitigate hallucinations, retrieval errors, tool misuse, prompt brittleness, and reasoning breakdowns.
- Define and measure quality metrics including accuracy, faithfulness, task completion, latency, cost, and robustness.
- Optimize production AI systems for scalability, latency, security, reliability, and cost efficiency.
- Collaborate with product, frontend, and backend teams to integrate AI capabilities.
- Mentor engineers, influence technical decisions, and contribute to AI technical strategy and roadmap.
Requirements
- Bachelor’s degree in Computer Science, Mathematics, or a related field required; a Master’s or Ph.D. is preferred.
- At least 5 years of industry experience building and deploying production machine learning systems, with significant LLM experience.
- Strong expertise in NLP, generative AI, transformer architectures, embeddings, and retrieval systems.
- Proven experience designing and deploying enterprise RAG systems.
- Experience building and evaluating complex agentic or multi-step LLM workflows.
- Knowledge of PyTorch, TensorFlow, Hugging Face, and distributed or cloud-based infrastructure.
- Experience optimizing real-time ML systems for performance, scalability, and reliability.
- Strong technical leadership skills and ability to influence cross-functional decisions and raise engineering standards.
Benefits
- Medical, dental, and vision plans.
- Paid parental leave.
- Monthly health and wellness allowance.
- Work-from-home office stipend and remote work environment.
- Lunch reimbursement for in-office employees.
- Three weeks of PTO in Canada.
Tech Stack
PyTorchTensorFlow
Categories
About Cresta
Cresta builds a generative AI platform for contact centers, combining AI agents, real-time agent assistance, conversation intelligence, and quality/coaching tools. It sells enterprise software to customer-support and sales organizations to automate and improve conversations across voice and digital channels. Founded in 2017 and headquartered in Sunnyvale, California, the privately held company counts brands such as Alaska Airlines, Cox Communications, Intuit, United Airlines, and Marriott among its customers.