Applied AI Engineer

Accountabilities:

• Build and operate the AI runtime, tool-calling capabilities, and orchestration infrastructure required for production agent workflows.

• Design model selection and routing strategies, balancing performance, latency, and operating costs.

• Implement and improve retrieval-augmented generation (RAG), grounding, and context-retrieval systems where they demonstrably improve output quality.

• Develop evaluation harnesses, golden datasets, and quality benchmarks to assess model and agent performance, support release decisions, and identify regressions or performance drift.

• Establish evaluation frameworks for AI quality and implement guardrails and safety controls, treating retrieved information and tool outputs as untrusted inputs.

• Take ownership of production AI behaviour, including reliability, latency, cost, and failure management.

• Collaborate with product teams to determine when agent-based solutions are appropriate and when alternative approaches will deliver better results.

• Partner with customers and product stakeholders to validate outcomes, identify valuable use cases, and prioritize development based on measurable impact.

• Apply an iterative, value-driven approach by proving the value of focused solutions before scaling successful implementations.

• Instrument AI systems and measure their impact, using evidence and performance data to guide product and engineering decisions.

• Integrate automated quality assurance, testing, quality gates, and regression checks into development and delivery pipelines.

• Help establish engineering standards and evaluation and safety practices across the team, while contributing to technical interviews, mentoring, and future team growth.

• Promote a culture of technical excellence, customer focus, pragmatic decision-making, and effective collaboration with product teams across the organization.

Requirements:

• Demonstrated experience shipping software powered by large language models (LLMs) or machine learning (ML) to real production users, beyond prototypes, demonstrations, or experimental notebooks.

• Strong understanding of AI evaluation methods and the ability to assess model and agent quality systematically rather than relying solely on prompt experimentation.

• Ability to treat cost and latency as fundamental engineering constraints when designing and delivering AI-powered systems.

• Clear communication skills, with the ability to explain technical decisions and trade-offs to engineers, product stakeholders, and customers.

• A pragmatic, outcome-oriented mindset, with the ability to prioritize work based on customer needs, measurable value, and practical delivery considerations.

• Strong engineering judgment and the ability to make informed decisions about where AI agents are appropriate and where simpler solutions are more effective.

The following experience is considered an advantage, but is not required:

• Experience building and operating production-grade AI agents or RAG systems, including understanding their operational challenges and failure modes.

• Experience implementing model routing strategies or delivering measurable reductions in AI infrastructure and operating costs.

• Experience building evaluation harnesses that inform release decisions, including LLM-as-a-judge approaches calibrated against human assessments.

• Familiarity with model fine-tuning, distillation, or other model optimization techniques.

• Strong programming skills in Python or C#/.NET.

• Experience grounding AI applications in structured, well-modeled business data.

• Background in system and platform architecture, including the ability to evaluate technical trade-offs and long-term implications.

• Experience developing or operating enterprise-scale software, with an understanding of reliability, security, and integration requirements.

• Productive use of AI-assisted coding tools, with the technical judgment to review, validate, and supervise their output.

Benefits:

• Opportunity to join a founding AI engineering team and help shape the platform's architecture, technical standards, and future development.

• Meaningful ownership of production AI systems supporting mission-critical customer workflows.

• Close collaboration with experienced engineering and product professionals across multiple teams.

• Opportunity to influence AI strategy, evaluation practices, safety standards, and team development.

• Exposure to practical applications of commercial AI models, agent orchestration, retrieval systems, and enterprise-scale software challenges.