• Design and implement workflows involving tool calling, multi-step reasoning, and structured outputs. • Build robust integrations and connectors with common internal systems such as Slack, Jira, email, calendar, CRM, and data warehouses. • Implement RAG (Retrieval-Augmented Generation) and knowledge systems for product and internal docs, ensuring citations and links to sources are included. • Build basic access control patterns, including SSO/AD group-aware retrieval and role-based response filtering. • Ship MVPs fast, iterate based on user feedback, and add necessary guardrails such as evals, logging, and retry/timeout behaviors. • Document workflows and provide simple runbooks to facilitate internal adoption.

• Understand business needs, provide actionable insights and recommendations based on analyses, and translate them into technical requirements and solution proposals. • Stay up to date with trends and advances in data science. • Apply pattern recognition techniques, including but not limited to computer vision, convolutional neural networks (CNNs), language models for natural language processing (NLP), large language models (LLMs), data analysis and predictive analytics (ML). • Ensure technical feasibility of proposed machine learning models, partnering with data scientists in designing and building solutions. • Test and validate data science solutions to ensure their effectiveness, quality, and compliance with requirements. • Engage the team and foster constructive discussions, extracting information, knowledge, and potential from the group toward a shared objective or larger outcome. • Help teams increase productivity, achieve better results, solve complex organizational problems, respond quickly to change, and strengthen their organizational culture.

• Build agent workflows that take an integration need from plan to implementation and validation with humans approving at the right checkpoints. • Create systems that synthesize context from codebases, docs, specs, telemetry, and historical incidents to make changes that match Datadog conventions and customer expectations. • Generate and evolve integration code and tests, including end-to-end scenarios that reflect real customer workloads and product features. • Design evaluation harnesses that prevent silent regressions: golden sets, scenario baselines, semantic checks, performance thresholds, and release gating. • Build portfolio-level automation: proactive updates for upstream breaking changes, tracer feature rollouts across the catalog, migrations to new schemas/semantics, and targeted coverage expansion. • Partner tightly with PM, support engineers, and integration-owning teams to make the system adoptable, trustworthy, and embedded in daily engineering workflows.

• Build agent workflows that take an integration need from plan to implementation and validation with humans approving at the right checkpoints. • Create systems that synthesize context from codebases, docs, specs, telemetry, and historical incidents to make changes that match Datadog conventions and customer expectations. • Generate and evolve integration code and tests, including end-to-end scenarios that reflect real customer workloads and product features. • Design evaluation harnesses that prevent silent regressions: golden sets, scenario baselines, semantic checks, performance thresholds, and release gating. • Build portfolio-level automation: proactive updates for upstream breaking changes, tracer feature rollouts across the catalog, migrations to new schemas/semantics, and targeted coverage expansion. • Partner tightly with PM, support engineers, and integration-owning teams to make the system adoptable, trustworthy, and embedded in daily engineering workflows.