About the role
Requirements:
- Bachelor's degree in computer science, engineering, or a related field; advanced degree preferred.
- 10+ years of professional software engineering experience, including recent, hands-on depth building of production AI/ML or LLM-based systems.
- Proven experience driving technical design and implementation across complex, distributed systems, from architecture through production delivery.
- Deep experience designing and scaling AI systems in production RAG pipelines, agentic workflows, and multi-model orchestration.
- Strong experience building cloud-native solutions (AWS/Azure/GCP) and the APIs, services, and integration layers that connect AI capabilities to enterprise systems.
- Experience integrating LLMs and agent frameworks with enterprise data and tooling, including connector/tool-use patterns (e. g., MCP) and retrieval and grounding strategies.
- Experience establishing CI/CD pipelines (GitLab or equivalent) and engineering best practices for reliability, security, and maintainability.
- Strong understanding of observability and monitoring for AI systems, including performance, cost, and quality/evaluation of model outputs.
- Experience implementing secure application architecture (identity management, SSO, secrets handling) and delivering solutions that meet enterprise security and compliance requirements.
- Demonstrated ability to set engineering standards and elevate technical maturity across a team through design reviews, mentorship, and hands-on leadership.
- Demonstrated ability to influence cross-functional stakeholders without direct authority.
- Strong ability to evaluate and communicate technical trade-offs in system design, including where to build, buy, or reuse.
- Experience using AI-assisted engineering tools to improve productivity, design quality, and system insight.
Must Have Skills:
- Hands-on experience building and deploying production AI systems using LLMs, RAG, agentic workflows, or multi-model orchestration.
- Strong experience with cloud platforms (AWS/Azure/GCP).
- Experience developing APIs and integration layers that connect AI capabilities to enterprise systems and data.
- Experience with agent and tool-use frameworks, including connector patterns (e. g., MCP).
- Experience building distributed systems and the services that support them at scale.
Nice-to-Have:
- Experience designing high-throughput, low-latency distributed systems at scale.
- Experience fine-tuning, evaluating, or optimising LLMs, including prompt engineering, evaluation frameworks, and inference cost/performance tuning.
- Experience with AI observability and quality output evaluation, hallucination detection, drift monitoring, or agent tracing.
- Experience with advanced API governance, versioning, and performance optimisation.
- Familiarity with frontend technologies (e. g., React) for full-stack architectural awareness when building end-user AI experiences.
- Experience leveraging AI for system insights, anomaly detection, or operational optimisation.
- Experience working in a forward-deployed, consulting, or customer-facing engineering model, translating business problems into technical solutions.
- Experience delivering solutions across multiple lines of business or domains, matching engineering effort to business value.