Search Architect

Essential functions

• The engineer is supposed to participate in pre-sales, discovery phases of projects and lead projects.

• They are also expected to be capable of starting the project from scratch and lead the team.

• Participate in building the AI community from the ground up.

• POC development with the Team

Qualifications

Tech stack

• Java, Spring

• Prompt engineering

  • Best practices for prompt engineering

  • How LLM can be used in applications for a variety of tasks

• NLP

  • General understanding of typical NLP problems: classification, NER, summarization, question answering, sentiment analysis, etc.

  • Theoretical intuitive understanding of how Transformers work (tokenization, attention, etc).

• Vector search

  • Vector databases, performance tuning

  • Document chunking techniques

• LLM applications development

  • Spring AI

  • Chain of Thoughts, DSP, and other techniques

  • Agents and tools

• Google cloud (GCP)

Requirements

• Rapid POC development to test ideas, reduce risks, and enable data-driven decisions for increased project confidence.

• Preferable, the engineer is expected to have IT services/consulting experience.

• Proficient in developing LLM-powered systems using advanced prompt engineering techniques, RAG and agentic design patterns. Experienced with frameworks like LangChain, LlamaIndex, and DSPy, Spring AI

• Familiar with evaluation approaches and metrics for different types of LLM-based systems.

• Experienced with keyword and vector search methods, including understanding of their underlying algorithms. Familiar with popular vector search engines.

• Competent in various document understanding models and techniques to parse complex documents and implement effective chunking strategies for RAG systems.

• Familiar with LLM and embedding models fine-tuning techniques.

• Competent in using joint vision-language and generative models to solve various problems related to image generation, visual question answering, and multi-modal search.

• Understanding of the challenges and risks associated with the development of Generative AI systems and how to mitigate them.

• Familiar with various architecture design patterns for different types of LLM-based applications such as chatbots, text2sql, document understanding, etc. Familiar with various approaches to scalability and cost reduction in Generative AI systems.

• Ability to stay updated with the latest advancements in Generative AI and integrate emerging technologies to drive innovation and improve the performance of AI systems.

• Familiar with Responsible AI principles and Human-AI interaction design best practices.

We offer

• Opportunity to work on cutting-edge projects
• Work with a highly motivated and dedicated team
• Competitive salary
• Flexible schedule
• Benefits package - medical insurance, vision, dental, etc.
• Corporate social events
• Professional development opportunities
• Well-equipped office

About us

Grid Dynamics (NASDAQ: GDYN) is a leading provider of technology consulting, platform and product engineering, AI, and advanced analytics services. Fusing technical vision with business acumen, we solve the most pressing technical challenges and enable positive business outcomes for enterprise companies undergoing business transformation. A key differentiator for Grid Dynamics is our 8 years of experience and leadership in enterprise AI, supported by profound expertise and ongoing investment in data, analytics, cloud & DevOps, application modernization and customer experience. Founded in 2006, Grid Dynamics is headquartered in Silicon Valley with offices across the Americas, Europe, and India.