Lead AI Product Engineer

Description

The creative mind behind every project. Put your skills to the test to build solutions that continue to shape the world we live in.

About Us

Ascent has recently been acquired by Acuity Analytics. This is both a significant milestone for us and a tremendous opportunity for you. Acuity Analytics is a business with a strong global reputation, an impressive client base and ambitious growth plans. We deliver deep insights and domain-led digital transformation to high-growth and heavily regulated organisations. To our customers, we bring a partnership that provides the talent, technology and capability to enhance performance and operational efficiency.

About the role

We are seeking a senior, hands-on engineer to design, build, deploy, and continuously improve AI-enabled applications used in day-to-day business workflows. This role sits across product engineering, cloud architecture, and production AI operations. You will work from the earliest stage of a project through release and ongoing support, while creating reusable patterns that improve delivery across the broader portfolio.

The defining requirement: demonstrated experience building products with live AI capabilities—not simply using AI tools to accelerate software development.

Responsibilities

• End-to-end delivery. Own solutions from discovery and architecture through implementation, phased testing, deployment, monitoring, and production support.
• Production AI features. Build AI capabilities into real applications and workflows, including model and service integration, grounding or retrieval patterns, structured outputs, orchestration, guardrails, and fallback behavior.
• Full-stack product engineering. Deliver intuitive web experiences, robust APIs and services, and reliable connections between the application, AI, and data layers.
• Reusable engineering foundations. Turn project work into shared components, templates, reference architectures, deployment patterns, and standards that can be applied across multiple initiatives.
• Quality and evaluation. Define how testing changes across development and deployment stages; implement automated software tests and repeatable evaluation of AI quality, reliability, latency, and failure modes.
• Observability and root-cause analysis. Instrument applications so AI, data, integration, and application behavior can be traced; diagnose issues across upstream and downstream dependencies and implement durable fixes.
• Security and governance. Embed authentication, authorization, secrets management, data protection, auditability, compliance controls, and lineage into the solution design.
• Cost and performance optimization. Measure and improve run cost, token consumption, model selection, retrieval strategy, caching, latency, and infrastructure use; clearly report the economics of operating each solution.
• User experience and adoption. Challenge designs that create poor user outcomes, partner with UI/UX and business stakeholders, and ensure the finished product is meaningfully more efficient than the underlying manual workflow.
• Technical leadership. Contribute ideas, review designs and code, share specialist knowledge with a lean cross-functional team, and take the lead when a challenge aligns with your technical strengths.

Requirements

• Significant professional software engineering experience, including ownership of production systems and technical decisions at Lead or Principal-caliber level.
• Hands-on delivery of AI-enabled products or application features that operate in production and serve recurring business workflows.
• Strong full-stack capability: modern JavaScript/TypeScript, React or Next.js, API and service development, and integration with enterprise data platforms.
• Strong backend engineering experience in C#/.NET or a comparable enterprise stack, with sound knowledge of distributed systems, asynchronous processing, and integration patterns.
• Deep experience with Azure or another major cloud platform, including secure networking, identity, secrets, serverless or containerized services, CI/CD, infrastructure as code, and production telemetry.
• Practical understanding of LLM application architecture, including model APIs, retrieval and grounding, prompt and context design, structured output, evaluation, monitoring, and responsible failure handling.
• Ability to explain trade-offs among quality, user experience, latency, security, maintainability, and cost—and make pragmatic decisions based on the operating context.
• A persistent, low-ego problem-solving style: able to work through ambiguity, seek expertise when needed, and remain accountable until the issue is resolved.
• Clear written and verbal communication, with the judgment to work directly with engineers, product partners, business stakeholders, and support teams.

Nice to Have

• Azure OpenAI or comparable managed model services, Azure AI capabilities, and production use of leading model providers.
• Application Insights, OpenTelemetry, distributed tracing, AI-specific observability, or evaluation tooling.
• Snowflake or comparable cloud data platforms, including patterns that move deterministic processing outside the LLM where appropriate.
• Enterprise design systems, accessibility, user research, and close partnership with UI/UX specialists.
• Regulated or data-sensitive environments such as financial services, insurance, or other enterprise settings.
• Working proficiency in Python for AI services, evaluation, data processing, or automation.

Benefits

People are at the Heart of our Business. By investing in people, we achieve exceptional results for our clients and create new opportunities for our teams to thrive. Check out this page for more details.