Senior Data / AI Engineer
Role details
Job location
Tech stack
Job description
As a Senior AI Engineer, you will design, build, and operate production-grade AI systems that power Alpian's next-generation banking experiences.
This role goes far beyond prompts and demos. You will apply strong software engineering discipline, data governance principles, and modern LLM techniques to deliver AI systems that are secure, observable, cost-aware, and trustworthy (i.e., the kind that belong in a regulated banking environment).
You will work at the intersection of LLMs, analytics, and data platforms, where BigQuery and analytical correctness matter just as much as agentic workflows.
Jobübersicht:
WHAT YOU'LL BE DOING:
- Design and implement LLM-powered platforms used by real customers and internal teams.
- Build agentic workflows with explicit state, tool/function calling, retries, and failure handling.
- Engineer robust (Agentic) RAG pipelines:
- Chunking and embedding strategies
- Metadata-aware retrieval and ranking
- Grounding
- Leverage analytics and data platforms as first-class AI inputs:
- Querying and modeling data in BigQuery
- Designing AI-friendly analytical schemas
- Ensuring correctness, consistency, and explainability of results
- Apply data governance and security best practices:
- PII handling and customer data isolation
- Access control, auditability, and traceability
- Make AI systems observable and measurable:
- Tracing, evaluations, and error analysis
- Latency and cost monitoring
- Write clean, maintainable Python code:
- Async APIs
- Proper testing strategies
- CI/CD pipelines and containerized deployments
- Act as a technical interface with stakeholders and partners, producing clear documentation and explaining trade-offs without hype.
- Provide clear technical documentation
- Explain trade-offs without hype or buzzwords
OUR STACK:
- Google ADK (Agent Development Kit)
- Google Vertex AI
- BigQuery (core analytical and AI data platform)
- Grafana (analytics, metrics, and data exploration)
- Python (async, APIs, testing, best practices)
- Vector databases & embedding models
- Cloud-native infrastructure on GCP
- CI/CD, containers, IAM, secrets management
Requirements
Do you have experience in SQL?, Do you have a Master's degree?, * 5-8+ years of experience in software or platform engineering, with recent production LLM systems.
- Strong Python expertise, including async programming, API design, testing, and production debugging.
- Hands-on experience with agentic frameworks, such as:
- LangGraph / LangChain Agents
- AutoGen
- CrewAI
- LlamaIndex Agents
- (Bonus: Google ADK)
- Deep, practical experience with RAG engineering:
- Vector databases
- Chunking & embedding strategies
- Metadata-driven search and ranking
- Strong experience working with analytical data platforms, including:
- Writing and optimizing SQL queries
- Understanding analytical data models and metrics
- Using analytics outputs as reliable AI inputs
- Proven track record building secure, observable, and cost-aware AI systems:
- Tracing, evals, guardrails
- IAM, secrets, and PII-aware architectures
- Strong software engineering fundamentals:
- APIs, CI/CD, containerization
- Structured, maintainable codebases
- Clear communicator who can work across engineering, product, and business teams.
NICE TO HAVE:
- Experience designing multi-tenant AI systems
- Strong experience with the Google Cloud (Data) Platform:
- BigQuery
- Vertex AI Agent Engine
- Gemini Enterprise
- Experience integrating AI outputs with a dashboarding tool (e.g., Grafana, Looker) or analytics workflows
- Familiarity with ML evaluation frameworks or LLM-as-judge approaches
- Background in regulated environments (finance, healthcare, etc.)
- Strong opinions about software engineering and Python best practices (earned the hard way)