Principal AI Engineer - Retrieval at Wesser

Bartlett, Illinois, United States -

Full Time

Start Date

Immediate

Expiry Date

16 Feb, 26

Salary

0.0

Posted On

18 Nov, 25

Experience

10 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

AI Engineering, Information Retrieval, Data Modeling, Machine Learning, Multimodal Models, Vector Databases, Embedding Models, Reranking Systems, Data Enrichment, Prompt Engineering, Evaluation Frameworks, Technical Leadership, Mentorship, Data Pipelines, Hybrid Search, Quality Monitoring

Industry

Software Development

Description

About Datagrid Forget everything you know about AI assistants. At Datagrid, we’re building AI agents that actually do the work. We’re a team of passionate, hard-working builders, thinkers, and problem-solvers who are genuinely excited about what we do. Our mission is to supercharge the workday by turning complex data and tedious workflows into simple, automated actions. It’s an incredibly exciting time to join us—we’re growing fast, expanding our platform’s capabilities, and partnering with enterprise customers who want to 10x their teams’ output. We thrive on collaboration and are looking for people who are ready to make a tangible impact. If you want to be part of a team that’s not just talking about the future of AI but actively creating it, you’ve come to the right place. Our Values At Datagrid, our values guide how we work, build, and grow together. Act with Purpose: Everything we do is tied to our mission. You’ll see the impact of your work as we move quickly to solve meaningful problems for our customers. Own the Outcome: We believe in true ownership. You’ll take responsibility for your projects and see them through to success—empowered to make decisions that drive real results. Clarity without Ego: We value honesty, transparency, and trust. You can expect and provide direct feedback in an environment where candor sharpens our ideas and strengthens our team. Creativity with Purpose: Innovation is central to our culture. Your creative thinking will be valued and directed toward solving real-world challenges and creating lasting impact. About the role: This is an opportunity to architect the core retrieval layer that powers our AI agents across 100+ enterprise data connectors. Our agents' success lives or dies by the quality of the information we provide them. They must surface the right information from massive, multi-modal datasets: construction blueprints, manufacturing specs, project videos, and enterprise documents—and deliver accurate answers in seconds. You will join the team building a world-class retrieval system that understands complex, domain-specific data and surfaces the right context, at scale, with sub-second latency. As a Principal AI Engineer, you will be the technical leader collaborating onindexing,advanced retrieval techniques, and multimodal inputs. You'll own end to end agentic retrieval components in our RAG pipeline. You will mostly be involved in post-ingestion workflows including knowledge indexing, retrieval and reranking. You'll design sophisticated strategies and work with custom vector embeddings to implement cutting-edge hybrid search. You will use evals to prove our retrieval quality is second to none. You'll work at the critical intersection of information retrieval, LLMs, VLMs, and production ML systems, while mentoring a growing engineering team to establish best practices for AI development. What you’ll do: Retrieval & RAG Architecture (Text & Multimodal) Design and optimize end-to-end RAG pipelines implementing advanced techniques including hybrid search, context compression, and query decomposition. Architect and deploy sophisticated reranking systems using cross-encoders, multi-vector models, and LLM-based rerankers to maximize the relevance of retrieved contexts. Optimize chunking strategies, embedding models, and vector database configurations for diverse document types including PDFs, videos, images, and structured data. Develop and implement multimodal embedding and retrieval strategies that capture semantic relationships across text, image, and video modalities. Implement techniques for visual understanding tasks like document layout analysis, image captioning, and video content extraction to feed the retrieval system. Data Enrichment & Contextualization Engineer data enrichment components that augment data with domain context to produce vector embeddings that dramatically improve precision and recall. Build systems that extract and normalize entities, relationships, and metadata from unstructured data to create a rich, queryable knowledge graph. Design and implement prompt engineering frameworks for query understanding and transformation, ensuring user intent is accurately captured before hitting the retrieval system. Evaluation & Quality Infrastructure Take ownership of and scale our comprehensive evaluation framework, incorporating traditional IR metrics, LLM-as-a-judge methodologies, and task-specific success criteria. Build automated quality monitoring systems that detect retrieval degradation, data drift, and "lost in the middle" problems before customers experience issues. Design A/B testing infrastructure for rapid experimentation with retrieval strategies, reranking models, and embedding models. Establish golden datasets and benchmark suites that enable continuous measurement of retrieval performance across diverse customer scenarios. Technical Leadership & Mentorship Provide hands-on mentorship to uplevel the team's capabilities in information retrieval, data modeling, and retrieval evaluation methodologies. Define technical standards and best practices for data-centric AI development, including data quality, testing protocols, and observability requirements. Lead architecture reviews and technical decision-making for the core RAG and data intelligence framework as the team scales. Collaborate closely with product managers and customers to translate complex data retrieval requirements into elegant technical solutions. What you'll have: Required Qualifications 7+ years of software engineering experience with 3+ years focused on production AI/ML systems, with demonstrated expertise building and scaling data-intensive LLM applications. Deep hands-on experience designing, building, and optimizing production RAG systems, including vector databases (e.g., Milvus, Pinecone), embedding models, and advanced retrieval strategies. Deep understanding of information retrieval fundamentals, including search indices (e.g., BM25), neural reranking, and hybrid retrieval strategies. Experience with multimodal models and vision-language understanding (e.g., CLIP, BLIP, GPT-4V) for processing images, videos, and complex documents. Proven track record building and scaling production data pipelines for search or ML systems (e.g., data enrichment, ETL, feature engineering). A deep understanding of LLM observability, debugging, and evaluation (e.g., Arize, Langfuse, MLflow). Production experience with prompt engineering techniques and systematic approaches to prompt optimization and testing. Demonstrated technical leadership experience mentoring engineers, leading architecture decisions, and establishing engineering standards. Track record of translating ambiguous customer problems into concrete technical solutions and measurable outcomes. Bonus Qualifications Hands-on experience with model fine-tuning (SFT) or training custom reranking models for domain-specific applications. Background working with enterprise data integration challenges across diverse data sources and formats. Contributions to open-source AI/ML projects or in information retrieval or multimodal AI. Experience building in highly regulated industries (construction, manufacturing, healthcare) with compliance and safety requirements. Salary & Benefits Generous equity compensation Flexible vacation/time-off policy All U.S. federal holidays observed, plus an additional company-wide Week of Rest in December Competitive benefits package - 100% premium coverage for employees and generous coverage for dependents Work-from-home stipend to support your ideal setup 401(k) plan Final offer amounts depend on multiple factors such as candidate experience and expertise, geographic location, total compensation, and market data. In addition to cash pay, full-time regular positions are eligible for equity, 401(k), health benefits, and other benefits; some of these benefits may be available for part-time or temporary positions.

Responsibilities

Architect the core retrieval layer for AI agents, ensuring the quality of information from multi-modal datasets. Lead the development of advanced retrieval techniques and mentor a growing engineering team.