SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Altana is building an AI-powered network for trusted global trade. The Implementation team is responsible for taking Altana's platform from signed contract to realized customer value—designing and deploying agentic AI systems, managing end-to-end customer implementations, and serving as a trusted technical partner throughout.
In this Staff-level role, you will design, build, and deploy agentic AI workflows that power customer business processes on real data. You'll ground agents in customer context by connecting them to data sources, APIs, and systems of record; write and refine prompts and system instructions for production reliability; build orchestration and human-in-the-loop checkpoints; and monitor, evaluate, and iterate on deployed processes.
You'll own technology implementation and delivery end-to-end: scoping, configuration, integration, validation, go-live, and handoff. You'll configure Altana's platform against real customer data and workflows, build the connective tissue (API integrations, data handoffs, automations, internal tooling) that makes implementations work, and drive implementations to adoption—not just deployment.
You'll engage customers as a trusted technical partner, serving as the primary technical point of contact through implementation. You'll run working sessions and technical deep dives, elicit requirements from customers who can't fully articulate them, translate business problems into technical scope, and manage expectations and scope with the directness that keeps large enterprise programs on track.
Internally, you'll coordinate across engineering, data science, product, and customer success teams. You'll escalate and unblock, feed field learning back into product, and build reusable playbooks and templates. You'll apply product management judgment: own implementation roadmaps for your accounts, sequence work by customer value and delivery risk, write clear requirements and specs, and define and track success in measurable terms.
The role is based in Australia with flexibility to travel onsite to the Canberra hub location.
REQUIREMENTS:
- 8+ years in customer-facing technical delivery (implementation, engineering, professional services, technical program management, or product management with hands-on scope)
- Demonstrated track record of shipping complex technical projects with external stakeholders, on real deadlines, with real consequences
- Strong communicator and coordinator; ability to run customer working sessions and drive internal alignment across teams
- Product instincts; naturally ask what problem this solves and what the smallest solution is
- Comfortable with ambiguity and partial information; make progress before the picture is complete
- Bias toward automation and repeatability over heroics
TECHNICAL COMPETENCIES:
- Working proficiency in Python or comparable language: read codebases, write and debug scripts, build integrations, ship small features
- Fluency with SQL and comfort exploring and validating data
- Practical experience with AI-assisted coding tools (Claude Code, Cursor, Copilot, or similar) as a core part of workflow
- Hands-on experience building or deploying agentic AI systems (LLM-powered agents, tool and function calling, retrieval-augmented generation, multi-agent orchestration)
- Skill in prompt engineering and agent evaluation; design prompts and evals, diagnose agent failures, iterate toward reliable production behavior
- Familiarity with agent frameworks and protocols (MCP, LangChain, or similar) and wiring agents to external tools, APIs, and data sources
- Familiarity with APIs (REST, Swagger/OpenAPI), Git-based workflows, and cloud-hosted systems
- Understanding of data pipelines, data modeling, and ML systems sufficient to scope work, diagnose issues, and hold credible conversations with engineers
NICE TO HAVE:
- Experience with global trade, supply chain, customs, or trade compliance
- Background in enterprise software implementation at scale (multi-stakeholder, multi-quarter programs)
- Exposure to Spark, Databricks, or large-scale data processing
- Experience building internal tooling or automation that a team adopted
- Formal product management experience (roadmaps, specs, stakeholder prioritization)
TECHNOLOGIES IN ENVIRONMENT:
Languages: Python, SQL, Spark
AI tooling: Claude Code and other AI-assisted development tools (used daily)
Agentic AI: LLM agents, tool and function calling, MCP, retrieval-augmented generation, agent orchestration frameworks
Platform & infrastructure: Docker, Git, Kubernetes, Swagger/OpenAPI, AWS, Azure
Datastores: Databricks, Elasticsearch, Postgres, Redshift
