Senior AI Engineer (LLM, Data)

Vecten is an AI-native data and technology partner for private capital and healthcare. Founded in 2010 and headquartered in Warsaw, we work with PE firms and VC funds managing a cumulative $1.2T+ in assets. Our average engagement runs five years. Our NPS sits above 80.

We've also done to ourselves what we do for clients. We restructured our own company around AI - tools, policies, roles, delivery models. You'll join a team that runs this playbook daily, not one that's still debating it.

The project

You'll work with our client, an American private equity and investment management firm - Fortune 500, based in New York. We support them in the area of infrastructure and data platform, and we build AI systems within that environment. The client works across finance, credit, investments, and real estate.

Snowflake is the central data warehouse. Much of your work will start with data that already lives there and end with an AI-powered system the client's teams rely on.

What you'll do

• Design and ship LLM-powered applications: prompt pipelines, RAG, retrieval, evaluation. From validated proof of concept to production.
• Deliver MCP servers that expose data and services to AI agents and applications.
• Implement the security and authentication layer around them: enterprise authentication, custom IdP integrations, OAuth/OIDC flows.
• Consume external APIs and wrap them into services - web services, traditional APIs, or basic UIs.
• Integrate LLM providers (OpenAI and others) into client systems.
• Build semantic search and retrieval on vector databases (Pinecone).
• Query, process, and analyze data in Snowflake using SQL and Python. Prepare datasets that feed AI features and analytics.
• Contribute to data pipelines when needed. Other team members own them day to day, so this stays occasional.
• Document design decisions before implementation.

Claude Code is your primary delivery environment. Agentic engineering is how we work, not an experiment on the side.

Requirements

AI / LLM

• Hands-on experience integrating LLMs in production: provider APIs, embeddings, RAG, vector semantic search.
• Experience with vector databases (Pinecone or similar).

Python and data

• Strong Python, with solid command of the typical Python data stack for analyzing and processing data.
• Strong SQL and hands-on Snowflake experience. Expect a lot of querying, processing, preparing, and analyzing.

Infrastructure and web services

• Good fundamentals in AWS (EC2, IAM, RDS, S3 and friends), Terraform, and Docker. You don't need to be the expert in the room, but you should have real experience and know your way around.
• Experience consuming and integrating external APIs.
• Experience building web services, APIs, or simple UIs.

General

• 5+ years of professional engineering experience.
• Undergraduate or graduate degree in Computer Science, Engineering, Mathematics, or a similar field.
• Comfortable working in both Windows and Linux environments. Your workstation runs Windows; part of the server estate does too.
• English at C1 or above, spoken and written.
• Clear technical writing. You document decisions and ask questions before they become problems.

Extra points for

• LLM fine-tuning experience.
• Working knowledge of MCP and MCP-based integrations.
• Background in statistics or machine learning - training and evaluating basic models with scikit-learn or PyTorch.
• Experience with agent frameworks.
• Working knowledge of OAuth 2.0 and OIDC flows.
• Airflow and dbt.
• Experience with FastAPI or other Python web frameworks.
• TypeScript or JavaScript, plus Next.js or React if UI work interests you.

Benefits

• Frontier work, not filler. You're not building another chatbot. These systems support investment decisions at one of the largest investors in the world.
• Real autonomy. Once we align on goals, you own delivery end to end. No process layers between you and the work.
• Senior collaboration. Small team, direct access to client stakeholders, real decisions. No filler meetings.
• Growth tied to output. Your impact on client outcomes directly shapes what you earn and how fast you grow here.
• Flexible working hours, remote or hybrid from our central Warsaw office.