Selection of the most suitable vacancies for you
Vacancy details
Data Engineering
Data Engineer
Senior
Poland, Spain
Remote
APPLY NOW
REFER A FRIEND
Our client is a leading global investment management company headquartered in London. It manages over $228 billion in assets and serves institutional investors, pension funds, wealth managers, and other sophisticated clients worldwide. The firm specializes in quantitative investing, alternative investments, systematic trading strategies, and technology-driven asset management. Data science, machine learning, and AI are core components of its investment and research processes.
As part of our collaboration we will focus on two foundational capabilities required to enable safe and scalable AI adoption across the enterprise: Agentic Security and AI-Ready Data Foundations.
What project we have for you
We build the data foundations that make AI useful and safe inside regulated financial firms. The value of AI is capped by the data its agents can reach: if an agent cannot find, interpret, trace or be correctly permissioned against data, the capability is useless, or worse, unsafe. Your job is to close that gap.
This is a hands-on senior role for an excellent Python engineer with strong data-engineering skills who is genuinely comfortable building with AI agents. You will design and build the catalogue, semantic, entitlement and analytical layers that turn large on-premise data estates into something agents can use.
What you will do
- Build the agent-facing discovery layer over the domain catalogues: skills and tools through which the client’s AI assistant finds, explains and retrieves datasets, market-data sources and curated reports.
- Implement semantic routing from natural-language questions to the correct library, symbol, field or report, based on catalogue metadata and step-by-step lookups instead of hard-coded per-source wiring.
- Implement guided intent elicitation: clarifying questions and candidate proposals that help users who do not know the internal vocabulary reach the data they need.
- Co-design governed lookup capabilities, such as an agent-consumable report-list API, together with the client team that owns the platform.
- Publish skills through the client’s marketplace and review process: versioning, evaluation coverage, staleness management, compliance with platform behaviour rules.
- Build the evaluation harness for discovery quality: representative user questions become automated acceptance tests, run before every release and reported before and after changes.
- Feed real usage back into the metadata layer: failed routings, ambiguous terms and missing descriptions logged as concrete catalogue improvements.
What you need for this
- 5+ years of production software development in Python, including 2+ years of hands-on LLM application development: tool and function calling, structured outputs, context management, disciplined prompt engineering.
- Experience building agent tools and skills: MCP servers or equivalent tool-integration frameworks, and packaged skills or plugins published to a central AI assistant platform.
- Retrieval and routing over structured metadata: semantic routing from a natural-language question to the right source, library or report; step-by-step narrowing of large candidate spaces through inexpensive lookups; hybrid lexical and semantic matching.
- Guided conversational discovery: clarifying questions, candidate suggestions with explanations, intent refinement grounded in catalogue metadata.
- Experience building against governed platform APIs and publishing through a managed review process, following platform rules on provenance, citation and freshness.
- Fluent English; able to work independently with client engineering teams: presenting designs, incorporating review feedback, and representing the delivery team in technical discussions.
- Evaluation discipline: test suites for routing correctness and answer quality, with releases gated on regression results, and the ability to help the team adopt the same standard.
- Readiness to extend an existing AI platform, with its gateway, marketplace and governance, instead of building a parallel one.
Will be a plus
- Symbology and instrument reference data: identifier regimes, entity resolution from company names to internal identifiers (market-data opening).
- Fund or strategy reporting and BI domain knowledge; co-design of governed lookup APIs with a client platform team (reporting opening).
- Production experience with embeddings, vector search and reranking; token-efficiency and cost optimisation of agent workflows.
- Knowledge graphs consumed at query time; evaluation frameworks with LLM-as-judge scoring.
- Day-to-day use of AI coding agents; good judgement in conversational UX, including when an agent should ask and when it should assume.
- Experience in financial services or regulated environments; client-facing experience.
What it’s like to work at Intellias
At Intellias, where technology takes center stage, people always come before processes. By creating a comfortable atmosphere in our team, we empower individuals to unlock their true potential and achieve extraordinary results. That’s why we offer a range of benefits that support your well-being and charge your professional growth.
We are committed to fostering equity, diversity, and inclusion as an equal opportunity employer. All applicants will be considered for employment without discrimination based on race, color, religion, age, gender, nationality, disability, sexual orientation, gender identity or expression, veteran status, or any other characteristic protected by applicable law.
We welcome and celebrate the uniqueness of every individual. Join Intellias for a career where your perspectives and contributions are vital to our shared success.
Skills
AI_tools
LLM
Python
