AI Engineer - Freelance - 100 % Remote from Europe
Posted 2 weeks ago by Intecfy
Negotiable
Undetermined
Remote
United Kingdom
Summary: This remote AI Engineer position involves designing and scaling LLM-powered agents for a B2B fintech scale-up focused on delivering financial services through AI. The role requires a hands-on approach to developing advanced data-retrieval pipelines and ensuring agent reliability. Candidates should have a strong background in Python and NLP, with a minimum of five years of experience. This is a long-term freelance engagement open to talent across the EU/EEA and the UK.
Key Responsibilities:
- Design & refine LLM agents using retrieval-augmented generation (RAG) and advanced data-retrieval pipelines.
- Build evaluation frameworks, metrics, benchmarks and automated tests to ensure agent reliability and fairness.
- Apply solid NLP fundamentals (tokenisation, embeddings, architecture know-how) and mitigate bias.
- Practise prompt engineering (few-shot, role-based, chain-of-thought) with tools like Weave, LangSmith or Laminar.
- Juggle token limits, cost and latency without sacrificing structured and high-quality outputs.
- Write modular and maintainable Python for data-intensive back-end services and rapid data processing.
Key Skills:
- Minimum 5 years experience of Python mastery for high-performance and data-heavy applications.
- Proven experience building production LLM agents with RAG.
- Deep understanding of AI evaluation methodologies and NLP core concepts.
- Strong prompt-engineering chops and a habit of systematic experimentation.
- Comfort working autonomously in an async and fully remote environment.
- Nice to Have: Vector databases (FAISS, Qdrant), MLOps, cloud infra (AWS/GCP/Azure), Fintech or RegTech exposure, Contributions to open-source LLM tooling.
Salary (Rate): undetermined
City: undetermined
Country: United Kingdom
Working Arrangements: remote
IR35 Status: undetermined
Seniority Level: undetermined
Industry: IT
This is a remote position. Intecfy is partnering with a stealth-mode, VC-backed B2B fintech scale-up on a mission to bring seamless financial services to one billion people through cutting-edge AI. We’re looking for a hands-on AI Engineer who can design and scale LLM-powered agents at lightning speed, while keeping code as clean as a Swiss bank vault. This is a long-term, freelance (B2B) engagement for talent based anywhere in the EU/EEA or the UK (±2 h CET).
Responsibilities
- Design & refine LLM agents using retrieval-augmented generation (RAG) and advanced data-retrieval pipelines.
- Build evaluation frameworks, metrics, benchmarks and automated tests to ensure agent reliability and fairness.
- Apply solid NLP fundamentals (tokenisation, embeddings, architecture know-how) and mitigate bias.
- Practise prompt engineering (few-shot, role-based, chain-of-thought) with tools like Weave, LangSmith or Laminar.
- Juggle token limits, cost and latency without sacrificing structured and high-quality outputs.
- Write modular and maintainable Python for data-intensive back-end services and rapid data processing.
Requirements
- Minimum 5 years experience of Python mastery for high-performance and data-heavy applications.
- Proven experience building production LLM agents with RAG.
- Deep understanding of AI evaluation methodologies and NLP core concepts.
- Strong prompt-engineering chops and a habit of systematic experimentation.
- Comfort working autonomously in an async and fully remote environment.
Nice to Have
- Vector databases (FAISS, Qdrant), MLOps, cloud infra (AWS/GCP/Azure).
- Fintech or RegTech exposure.
- Contributions to open-source LLM tooling.
Benefits
- Competitive European day rate and the freedom of true freelancing.
- Ownership & autonomy from day one, your impact is immediate and visible.
- Annual learning budget for conferences, courses and certifications.
- Well-being allowance for gym, sports or that standing desk your back keeps begging for.
- Inclusive Environment: we value diverse perspectives and believe in the strength of an inclusive team.