• The Flex platform helps clients develop a comprehensive compliance program, leveraging technology to instill a culture of safety and maintain a productive workplace. • The platform combines features that are tailored to the needs of our client’s business, including audits and inspections, incident management, flexible training, and reporting and insights. • Lead the design, development, and scaling of the Agentic AI Platform, transforming the mature Enterprise EHS/ESG SaaS system (Flex) into a dynamic, AI-native system of intelligence and action. • Comfortable writing complex state-machine routing code in Python, deploying auto-scaling serverless pipelines on AWS, configuring secure vector search engines, and designing dynamic widget-rendering APIs for the frontend. • Built and shipped enterprise-grade AI products to production, managing real-world challenges of multi-tenancy, PII redaction, token costs, latency, and model hallucination.

• Own the AI platform roadmap: Define and drive strategy and execution for model serving, the LLM gateway, agent orchestration, and the infrastructure that keeps models and agents running reliably in production -- partnering with data engineering to define what the AI platform needs from the data layer without owning it directly. • Bridge platform and product teams: Own the seams between infrastructure and the teams shipping AI-powered product features, ensuring agent capabilities are governed, discoverable, and consistently delivered. • Own AI monetization as a product surface: Map agent activity to consumption-based AI credits, ensure logging infrastructure supports that mapping, and surface usage and cost data to enterprise admins. • Make evaluation and observability first-class: Ship pre-deployment eval gates plus production tracing, monitoring, alerting, and regression detection so you catch quality issues before customers do. • Build the AI governance and responsible AI layer: Own output-quality guardrails, agent access controls, data classification, audit logging, and enterprise compliance (SOC 2, EU AI Act, ISO 42001) as a horizontal control plane across every AI feature -- including the responsible AI framework governing how we evaluate bias, fairness, and safe agent behavior. • Define the AI admin experience: Own the controls governing which AI features are on or off and for whom, and which usage, cost, and audit data gets surfaced to enterprise admins.

Role Description We are looking for a motivated Agentic AI & AWS Engineer to help design, build, and improve AI-powered applications and workflows centred around the Anthropic and AWS ecosystem. - Build AI agents and multi-step workflows using Claude and related technologies - Design and improve RAG pipelines and knowledge retrieval systems - Develop integrations with APIs, databases, SaaS platforms, and internal tools - Deploy and maintain AI applications on AWS - Create evaluation, monitoring, and optimization workflows for AI systems - Implement tool use, function calling, MCP integrations, and agent orchestration patterns - Collaborate on architecture decisions and technical problem-solving - Stay current with developments in AI, Anthropic, AWS, and agentic systems Qualifications - Approximately 2+ years of software engineering, AI engineering, or related experience - Practical experience building applications using LLMs in real-world projects - Hands-on experience with: - Agentic AI systems - Retrieval-Augmented Generation (RAG) - Claude or other advanced foundation models - Python, LangChain, LangGraph - REST APIs and integrations - AWS certifications (Cloud Practitioner, Solutions Architect, Associate-level, or higher) are a plus! - Understanding of cloud-native architectures and deployment practices - Strong problem-solving ability and willingness to learn independently - Excellent written communication skills in English Requirements - Experience with Claude, Amazon Bedrock, or Anthropic technologies - AWS Solutions Architect, Developer, Machine Learning, or Data Engineering certifications - Experience with vector databases and semantic search - Familiarity with LangGraph, agent frameworks, MCP, or workflow orchestration tools - Experience deploying containerised applications - Knowledge of evaluation frameworks, observability, and AI testing methodologies - Open-source contributions, technical blogging, research projects, or portfolio projects Benefits - Flexible remote engagement with project-based work and long-term opportunities for high performers. - Exposure to real-world AI deployments across agentic systems, RAG, automation, and cloud-native applications. - The opportunity to work within the Anthropic and AWS ecosystem and gain practical experience with modern AI engineering workflows. - Access to relevant training, certification opportunities, and continuous learning resources as they become available through our network and partners. - Collaboration with experienced engineers and AI practitioners focused on practical, production-ready solutions. - Involvement in enterprise and client-facing projects where your work can have a direct business impact. - A culture that values ownership, initiative, curiosity, and continuous improvement. - The possibility of expanding your role and responsibilities as Datavent continues to grow. Application Instructions When applying, please include: - Your CV - Links to GitHub, LinkedIn profile, portfolio, and technical projects - AWS certifications achieved - A brief description of the most interesting AI system, agent, or RAG application you have built - Why you are interested in working with the Claude and AWS ecosystem To ensure a fair and consistent review process, only applications submitted through the official application portal will be considered.

• Design, develop, and productionize advanced agentic systems that: • Handle large volumes of security event data • Operate with resilience in noisy, real-world environments • Continuously evolve as new attack patterns and tools emerge • Improve and harden existing agentic systems • Work with LLMs in production environments, not just prototypes • Engineer robust context pipelines for large-scale data ingestion and reasoning • Optimize systems for performance, reliability, and failure handling • Evaluate and integrate new agent frameworks, tools, and approaches • Rapidly hypothesize -> build -> test -> validate -> iterate