Senior developer building production AI agents for Knak’s enterprise email and landing - page platform. Developing agent runtimes, evaluations, APIs, and AWS infrastructure.
About the role
- Staff AI Engineer building retrieval, inference, and agentic systems for Acquia’s Drupal-based digital experience platform. Shipping shared AI capabilities that turn enterprise data signals into customer workflows.
Responsibilities
- Write and ship production AI code daily as an active contributor
- Lead customer-context retrieval across semantic retrieval, indexing, and knowledge graph approaches
- Enable agents to resolve customers and retrieve their full context in a single request
- Build inference and signal layers over the Iceberg-based lakehouse
- Write scored inferences back to the data platform and expose signals through contracts for other teams
- Turn signals such as churn risk, usage and entitlement mismatch, and expansion opportunities into actionable workflows
- Select appropriate large models, small fine-tuned models, or deterministic code for each workload
- Manage inference costs
- Own evaluation and observability for AI systems
- Establish patterns for other teams and collaborate with engineering and business leaders to deliver company goals
- Work across observability, the core data platform, and insights and intelligence alongside product and platform teams
- Design, build, and ship production systems while iterating quickly
Requirements
- 8+ years of software engineering experience, including 3+ years shipping AI or ML systems to production
- Strong programming fundamentals and deep proficiency in at least one language used for AI and data work; Python is the primary language for ML and insights
- Fluency working with data at scale, including advanced SQL, a transformation layer such as dbt, and a distributed query engine over lakehouse or warehouse storage
- Experience reasoning about query cost and partitioning
- Production retrieval and context engineering, including embeddings, vector search, hybrid or graph retrieval, and measuring retrieval effectiveness
- Experience with agentic systems and durable workflows in production, including tool calling, state and memory, and human-in-the-loop patterns
- Experience with evaluation and observability for AI systems, including tracing, prompt and version management, and dataset-driven testing
- Cloud deployment experience, preferably AWS, with containerized services and inference cost ownership
- B.S. in Computer Science or equivalent practical experience
- Experience with shared data or ML capabilities used by other teams
- Experience with small and fine-tuned models, including distilling task-specific models
- Observability data fluency, including OpenTelemetry and high-volume logs, metrics, and traces
- Data governance knowledge covering access control, lineage, and data residency
- Enterprise SaaS or CMS experience; familiarity with Acquia's Drupal-based DXP
- Familiarity with AI-assisted coding tools such as Claude, Cursor, or Copilot, and MCP or similar technologies
- Strong communication skills for presenting AI system design to engineers and C-suite stakeholders
- Senior individual contributor track record and mentoring through technical work
- AI fluency, orchestration mindset, radical adaptability, builder mentality, and intellectual humility
Benefits
- Competitive healthcare coverage
- Wellness programs
- Take it when you need it time off
- Parental leave
- Recognition programs
- Inclusive, transparent, efficient, and educational interview experience
- Opportunities to grow your career and learn from a global team
Job title
Job type
Experience level
Salary
Not specified
Degree requirement
Tech skills
Location requirements
Report this job
Found something wrong with the page? Please let us know by submitting a report below.
Group Product Manager leading product managers and delivery for Caseware’s AI audit platform. Coordinating agents, evaluation tools, and AI workflow innovation at Canadian fintech Caseware.
Staff Software Engineer building AI/ML and evaluation infrastructure for Thumbtack's home - services marketplace. Designing scalable GenAI platforms, model systems, and developer tooling.
Staff Software Engineer building scalable AI/ML platforms and evaluation systems. Enabling Thumbtack’s home - services marketplace and GenAI - powered customer experiences.
Senior Software Engineer owning end - to - end AI - powered cybersecurity product development at Sophos. Building LLM - driven workflows, automation, interfaces, APIs, and scalable systems.
AI/ML developer intern building cloud - native software for Kinaxis, a global supply - chain orchestration company. Developing ML pipelines, models, and reliable platform capabilities.
Applied AI Engineer building LLM - powered pipelines that transform municipal websites into structured CMS content. Automating migration, validation, and internal tooling for SimpliCity’s Canadian GovTech platform.
Senior Java Developer with AI experience building ELITS cloud software products. Leading Java, Kubernetes, CI/CD, architecture, and developer mentoring for Montreal’s hybrid team.
Software Architect building next - generation AI agents and automation for Jerry.ai’s insurance marketplace. Scaling voicebots, LLM systems, and external - system workflows across physical - asset services.
Senior frontend - focused engineer building Pebl’s conversational AI assistant. Shaping streaming, agentic UX for a platform enabling global hiring and workforce management.