Highspring is a consulting and professional services partner that helps organizations modernize their platforms, processes, and operating models. We work side‑by‑side with our clients to design and deliver scalable, secure, and forward‑looking technology solutions across highly regulated industries, including financial services. Our teams combine deep engineering expertise with strong domain knowledge to build platforms that are reliable, auditable, and ready for enterprise scale.
The Opportunity
Highspring is supporting a large‑scale transformation initiative focused on applying Generative AI across institutional Lending platforms. We are seeking a hands‑on GenAI Technical Specialist who will design, build, and operationalize shared AI capabilities used across multiple Lending business lines. This role offers a clear growth path toward platform ownership, with responsibility for defining shared GenAI standards, architectures, and operational practices across the Lending domain.
What You’ll Do
- Design, build, and evolve reusable Generative AI workflows leveraged across multiple Lending use cases.
- Develop an enterprise‑grade AI document ingestion and data extraction capability, including traceability, confidence scoring, and human‑in‑the‑loop review.
- Build AI‑powered assistants embedded within Lending systems using agentic and tool‑based workflows.
- Deliver automated content and presentation generation workflows to support reporting, approvals, and governance processes.
- Provide expert guidance on GenAI architecture, including model selection, orchestration patterns, and evaluation strategies.
- Establish and operate LLMOps practices, covering extraction accuracy, assistant reliability, prompt lifecycle management, and audit monitoring.
- Design and implement controls for entitlements and PII handling when using open‑source and proprietary models in regulated environments.
- Act as a senior technical contributor with a path toward becoming a platform owner for shared GenAI capabilities across Lending.
What You Bring to the Table
- 2+ years of dedicated, hands‑on experience designing and operating Generative AI solutions in enterprise production environments.
- 5+ years of front‑to‑back engineering experience, with a strong focus on AI/ML platforms and workflows using Python or Java.
- Proven experience building and operating production‑grade GenAI / LLM platforms using patterns such as RAG, tool or function calling, agentic workflows, and validated structured outputs.
- Strong LLMOps expertise, including evaluation harnesses, prompt and version management, regression testing, observability, and reliability measurement in live systems.
- Hands‑on experience building AI‑first data ingestion pipelines with measurable accuracy, quality, and reliability.
Core Skills Required
- Advanced retrieval and vector search experience, including multi‑vector and late‑interaction approaches (e.g., ColBERT, advanced chunking).
- Experience designing multi‑stage retrieval pipelines with metadata filtering, re‑ranking, and quality trade‑offs.
- Strong understanding of retrieval and RAG evaluation metrics and how they impact system design (e.g., recall vs. precision, latency vs. quality, MRR, NDCG).
- Experience operating GenAI systems through real production failures such as model regressions, retrieval degradation, prompt drift, and data quality issues, with demonstrated mitigation strategies.
Our Stack
- Generative AI and LLM platforms with RAG and agentic architectures
- Python and Java‑based AI/ML platforms
- Vector databases and advanced retrieval frameworks
- Enterprise observability, evaluation, and governance tooling
- Frontend integration with modern frameworks (Angular or React) where applicable
Sign in
To continue your applicationor continue with email
By continuing you agree to our Terms & Privacy Policy.
