AI/ML Engineer

Andersen is hiring an AI/ML Engineer for a project developing an AI-native talent intelligence platform and improving candidate matching and recruitment efficiency.

The customer is an international company focused on delivering innovative digital solutions and technology-driven services. The organization supports businesses in improving operational efficiency, streamlining processes, and accelerating digital transformation initiatives. By leveraging modern technologies and industry best practices, the company develops scalable and secure solutions tailored to evolving business needs. The customer operates in a dynamic environment, emphasizing innovation, collaboration, and the continuous enhancement of products and services to create long-term value for its clients.

The project is focused on developing and enhancing an AI-native talent intelligence platform for the European market. It provides intelligent candidate-job matching through advanced CV analysis, skill normalization, hybrid search, and ranking capabilities, aiming to improve the accuracy and efficiency of talent discovery and recruitment.

Responsibilities:

• Owning the learning-to-rank stack end to end, including training data, features, model development, offline evaluation, production serving, and regression analysis.
• Improving the LambdaMART reranker and determining when gradient boosted trees are the appropriate solution.
• Designing and maintaining the offline evaluation framework, including NDCG@K, Precision@K, negative sampling strategies, dataset construction, and analysis of the gap between offline metrics and production behavior.
• Designing hybrid retrieval systems combining BM25 and dense vector search.
• Owning the recall budget feeding the reranker.
• Building feature sets for structured candidate-to-job matching, including skills coverage, seniority alignment, location and mobility signals, recency, and evidence strength.
• Handling sparse and partially populated profiles as a core design requirement, including calibration and monotonic constraints where needed.
• Diagnosing ranking quality regressions in production and identifying whether the root cause is related to features, labels, indexes, or models.
• Ensuring ranking decisions are explainable enough to satisfy Annex III obligations and support recruiter-facing explanations.
• Defining technical direction for matching systems.
• Reviewing contributions from other engineers working on the matching stack.
• Mentoring engineers on ranking fundamentals.
• Transforming interview transcripts and extracted claims into ranking features and supervision signals.
• Designing LLM-as-judge and weak supervision approaches for pairwise labels while managing label noise and consistency.
• Working on constrained extraction and span grounding to ensure claims are traceable to candidate statements.
• Contributing to interview integrity signals and confidence representation downstream.
• Using LLMs as components within larger systems rather than as core ranking models.

Must-have:

• Hands-on Machine Learning experience for 5+ years, with a focus on search, ranking, recommender systems, or relevance systems.
• Eperience building and operating production-grade ranking and retrieval systems for 3+ years.
• Strong practical experience with Learning-to-Rank, including gradient-boosted tree models such as LightGBM or XGBoost.
• Ability to explain and apply pairwise and listwise ranking objectives, selecting the appropriate approach based on real-world trade-offs.
• Strong expertise in ranking evaluation, including the development and maintenance of offline evaluation pipelines.
• Strong experimental rigor, including designing meaningful baselines; running ablation studies; distinguishing genuine improvements from noise, particularly with small or noisy evaluation datasets; reading and reproducing relevant research papers.
• Practical experience working with sparse, incomplete, or noisy data, including appropriate feature-engineering techniques.
• Experience generating scalable training signals without relying on manual annotation.
• Strong Python and ML engineering skills, including hands-on experience with scikit-learn.
• Ability to communicate complex technical topics clearly to both technical and non-technical stakeholders, including recruiters and compliance teams.
• Ownership of the full ranking funnel, from retrieval and recall through reranking and evaluation, including diagnosing ranking regressions and their root causes.
• Ability to approach data quality as a modeling challenge and balance relevance, latency, inference cost, and model complexity.
• Experience delivering production ML solutions independently, without relying on large infrastructure teams.
• Background in search, ads ranking, recommender systems, or marketplace ranking.
• Experience designing ranking benchmarks or evaluation metrics.
• Applied research experience through relevant publications or industrial research that resulted in production solutions.
• Level of English - from Upper-Intermediate and above.

Nice to haves:

• HRTech experience.
• Recruitment technology experience.
• Job marketplace or talent-matching experience.
• Vespa, Elasticsearch, or OpenSearch expertise, including index design and query tuning.
• Production experience with vector search technologies such as Vespa, FAISS, Qdrant, and Pinecone.
• Experience with model ensembling, including stacking and blending.
• Experience building regulated or auditable ML systems.
• LLMOps and experiment tracking experience.
• Experience with LangFuse.

Reasons why this job would be interesting to you:

• Experience in teamwork with leaders in FinTech, Healthcare, Retail, Telecom, and others. Andersen cooperates with such businesses as Samsung, Siemens, Johnson & Johnson, BNP Paribas, Ryanair, Mercedes, TUI, Verivox, Allianz, T-Systems, etc.
• The opportunity to change the project and/or develop expertise in an interesting business domain.
• Job conditions - you can work both fully remotely and from the office or can choose a hybrid variant.
• Guarantee of professional, financial, and career growth! The company has introduced systems of mentoring and adaptation for each new employee.
• The opportunity to earn up to an additional 1,000 EUR per month, depending on the level of expertise, which will be included in the annual bonus, by participating in the company's activities.
• Access to the corporate training portal, where the entire knowledge base of the company is collected and which is constantly updated.
• Bright corporate life (parties / pizza days / PlayStation / fruits / coffee / snacks / movies).
• Certification compensation (AWS, PMP, etc).
• Referral program.
• Private health insurance and sports compensation, depending on the type of employment.

Your personal data is protected in accordance with GDPR regulations. Learn more: https://andersenlab.com/privacy-policy

Join us!

https://people.andersenlab.com/