The Opportunity We are seeking a highly skilled and hands-on Senior AI Search Engineer with a strong foundation in data science, data engineering, and cloud-based AI solutions. This role focuses on designing and implementing intelligent search and question-answering systems powered by large language models and vector-based retrieval techniques. You will lead the development of scalable data pipelines, vectorization strategies, and Retrieval-Augmented Generation (RAG) architectures using platforms like Google Vertex AI and Azure AI. The ideal candidate combines deep technical expertise with strong problem-solving abilities and a passion for building impactful AI-driven user experiences.
We exist to unlock a better way to experience the world. Valtech is one of the largest global business transformation agencies. We design, build, and deliver transformative digital solutions for the world’s best-known brands. We engage with our clients worldwide to discover new opportunities, design & build digitally driven solutions, and run & continuously optimize outcomes. We build intuitive, frictionless, and connected experiences that improve human lives and make our client’s businesses grow.
We are also open to hiring more veterans and internally displaced persons. We invite you to explore the Valtech Ukraine: Diversity & Inclusion Annual Report 2024 to learn more about how we are putting our commitment to diversity and inclusion into action.
The ideal candidate’s skills include: * 3-5+ years of hands-on experience in a Data Engineering, Machine Learning Engineering, or Data Scientist role with a focus on building data-intensive applications * Google Cloud Platform (GCP): Proven experience with Vertex AI, specifically AI Applications (formerly Generative AI App Builder). Strong familiarity with Vertex AI Pipelines, Cloud Storage, BigQuery, and Cloud Functions * Microsoft Azure: Proven experience with Azure AI Search (formerly Cognitive Search), including creating indexes, data sources, and skillsets. Familiarity with Azure Blob Storage, Azure Functions, and Azure OpenAI Service * Expert-level proficiency in Python * Hands-on experience with relevant libraries such as LangChain, LlamaIndex, pandas, google-cloud-aiplatform, and azure-search-documents * Strong understanding of Natural Language Processing (NLP) concepts * Knowledge of vector embeddings, vector similarity metrics (e.g., cosine similarity, vector databases/indices * Practical experience designing and implementing RAG architectures * Strong SQL skills and demonstrable experience building production-grade data pipelines * Upper-Intermediate English level * Accountability, strong communication, collaboration, and time-management skills in cross-functional teams * Strong desire to learn more about business every day
Optional: * Experience with Infrastructure as Code (IaC) tools like Terraform or Bicep * Familiarity with containerization technologies such as Docker and orchestration with Kubernetes (GKE/AKS) * Experience with fine-tuning large language models * Experience with experience analytics data and utilisation of it to optimise search results * Experience building and exposing services via REST APIs for consumption by web applications * Knowledge of advanced search concepts like semantic ranking, query expansion, faceting/filtering, autocomplete, controls etc. * Relevant certifications (e.g., Google Professional Data Engineer, Google Professional Machine Learning Engineer, Azure AI Engineer Associate)
The Role Your responsibilities will be: * Design & Architect AI Search Solutions: Design end-to-end, scalable, and robust AI search and question-answering systems using Vertex AI Search or Azure AI Search * Develop Data Ingestion & Processing Pipelines: Build and maintain reliable ETL/ELT pipelines to ingest, cleanse, and transform large volumes of website, structured and unstructured data (e.g., PDFs, DOCX, HTML, database records) and experience analytics data (e.g. GA4) for indexing * Implement Vectorization and Indexing Strategies: Utilize embedding models (e.g., from Vertex AI or Azure OpenAI) to generate vector representations of data * Implement Vectorization and Indexing Strategies: Configure and manage search indices in Vertex AI Search, Azure AI Search or similar platforms, implementing hybrid strategies that combine vector search with traditional full-text and semantic search * Integrate Generative AI Models (LLMs): Build and optimize Retrieval-Augmented Generation (RAG) workflows by integrating the search/retrieval component with large language models (e.g., Google’s Gemini, models via Azure OpenAI) * Integrate Generative AI Models (LLMs): Develop and refine prompts to ensure accurate, relevant, and safe generative outputs * Build and Deploy MLOps Pipelines: Use Vertex AI Pipelines or Azure Machine Learning pipelines to automate the data processing, indexing, and model deployment lifecycle, ensuring reproducibility and efficiency * Evaluate and Optimize Performance: Develop metrics and frameworks to evaluate the performance of the search and generative systems, focusing on relevance, latency, accuracy, and user satisfaction * Evaluate and Optimize Performance: Continuously tune retrieval parameters, re-rank results, and experiment with different embedding models and prompts to improve performance * Collaborate and Innovate: Work closely with product managers, engineers, analysts and business stakeholders to understand user needs, define requirements, and deliver impactful AI-driven features
Benefits
Mental and physical health: * Medical insurance * Sports reimbursement budget * Home office support * A number of free psychological and legal consultations * Maternity and paternity leave support
Personal and professional development: * Internal workshops and learning initiatives * English language classes compensation * Professional certifications reimbursement * Participation in professional local and global communities * Growth Framework to manage expectations and define the steps to move towards the selected career * Mentoring program with the ability to become a mentor or a mentee to grow to a higher position
Valtech Ukraine has a system of progressive benefits packages in place — the longer you stay with the company — the more benefits you get.
For us, at Valtech, our main priority has always been people. Valtech has created One Fund to support Ukrainian colleagues who have found their lives turned upside down at these tough times. Our recruitment flow 1. Screening — we are going to send you a short questionnaire with few questions before we will invite you to first meeting with Talent Acquisition Consultant.
2. HR Interview — up to 1-hour interview with a Talent Acquisition Consultant.
3. Technical Interview — up to 1-hour technical discussion with our experts.
4. Final Interview — up to 1-hour soft skills meeting with the Delivery Manager and People Partner.
5. Collecting references — we will ask you to provide some references you already got from previous projects or 2/3 e-mail addresses to people of your choice that will be able to respond to our short survey.
With the rapid company growth, not only you get to be a part of constant evolution, but you can lead the change. The more we grow — the more opportunities there are to take on the responsibility, implement your creative ideas, and be the innovator and driver rather than the task executor.
