Agentic Engineer, Autonomous Logistics
About the company
We are a team within Scania Logistics working towards a bold ambition: autonomous logistics at global scale. Across logistics, we are rethinking how work gets done—building towards intelligent systems that can sense change, make decisions and act, with people setting direction and remaining accountable. We bring together AI, engineering and deep operational knowledge. We believe the people closest to the work are our strongest lever for transformation. Together, we challenge established ways of working, test ideas against real constraints and build evidence for where autonomy creates value. You will join a team with a clear strategic direction and meaningful room to shape how we deliver it. The opportunity is to turn emerging technology into operational capability—and help define what autonomous logistics becomes at Scania.
Your tasks
Embedded in Scania Logistics to build and scale governed agentic workflows across order-to-delivery. Autonomous logistics does not fail on ambition or ideas; it fails on the last mile between a proven demo and a governed production system. That last mile is exactly what this role owns, and each competency below is chosen against the goal, not against a generic job ladder. Design, build and operate production agentic workflows that take real order-to-delivery work, read approved context and enterprise data, use tools to act, and hand to humans at defined control points. The role turns proven proof lanes into reusable, governed capability that stays Scania-owned, and is measured on production outcomes rather than prototypes.
- Build agent workflows. Tool and function calling, orchestration and reasoning loops, state and memory, not just prompts.
- Engineer tools and integrations. Define tool and API contracts with permissions, retries and error handling, so agents act safely on order-to-delivery systems.
- Own evaluation. Build regression and trajectory evals (tool choice, policy compliance, outcome quality) and wire them into CI as quality gates.
- Guardrails and governance. Approvals for irreversible actions, audit logging, sensitive-data handling and prompt-injection defense, written as policy in code.
- Human-in-the-loop by design. Decide where humans review or approve, define escalation, and instrument the agent-to-human handoff (governed autonomy).
- Ground the agents. Retrieval, memory and context engineering, including MCP, so agents are grounded in Scania data with citations.
- Productionize and operate. Observability and tracing, cost and latency control, safe rollout and incident response across the lane portfolio.
Requirements
What matters most: the ability to build governed agentic workflows and to evaluate them honestly. Everything else strengthens the fit but is not required.
- Built with agents. Hands-on with LLM agents and tools; you know what holds up in production, not just demos.
- Evaluation as a discipline. You design evals and treat them as the hardest and most important part of the work.
- The modern agent stack. Comfortable with orchestration (the OpenAI Agents and Anthropic SDKs), MCP, vector search and RAG, tracing and eval tooling. Good to have: a logistics or supply-chain operations background, and strong software engineering (Python, APIs, distributed-systems thinking). Either is a real plus, and the blend of both is the ideal profile.
What we offer
We offer a dynamic and engaging workplace where collaboration, innovation, and continuous improvement are part of everyday life. You will be part of a strong team environment that encourages knowledge sharing and close cooperation across functions. With a structured development plan and a wide range of training opportunities, Scania supports your professional growth both locally and internationally. Benefits include access to our health center in Gröndal or a wellness allowance, result bonus, flexible working hours, and company car leasing. Scania also arranges events for employees and their families, and for those living in Stockholm, convenient commuting is supported through direct Scania Job express buses to Södertälje.
How to apply
Your application should include a CV and any relevant certificates. We welcome all applicants and strive for diversity in our recruitment processes. Apply as soon as possible, no later than 2026-11-26. Screening will take place on an ongoing basis during the application period. Logical and personality tests may be used as part of the selection process, and a background check may be required for this role.
If you have questions or would like more information, please contact: Johan Lindahl, Group Manager Process and IT - Central Solutions, johan.lindahl@scania.com We are looking forward for your applications!
Other
How this differs from adjacent roles This is not an ML engineer training models, a data scientist or analyst producing insight, or a developer shipping deterministic software. It owns the deployed, non-deterministic agent system at runtime: tool routing, guardrails, evaluation of stochastic behavior, and the cost, latency and safety of agents that decide and act. Strategy and ownership already sit in the team.