Sr AI/Agentic Engineer

Lendistry is an Equal Opportunity/Affirmative Action Employer. We consider applicants without regard to race, color, religion, age, national origin, ancestry, ethnicity, gender, gender identity, gender expression, sexual orientation, marital status, veteran status, disability, genetic information, or membership in any other group protected by federal, state, or local law.

If you need assistance or accommodation due to a disability, you may contact us at hr@ lendistry.com

Lendistry does not accept unsolicited resumes from recruiters, employment agencies, or staffing firms. To conduct business with Lendistry, a Master Services Agreement (MSA) must be executed and confirmed prior to submitting any information relating to a potential candidate. Without a signed MSA, Lendistry shall not be responsible to any individual or entity for any payment relating to any form of fee or compensation.

And, in the event that a resume or candidate is submitted by a recruiter, an employment agency, or a staffing firm without a fully executed MSA, Lendistry has the unrestricted right to pursue and hire any of those candidate(s) without any legal or financial responsibility to the recruiter, agency, and/or firm.

A Day in the Life

The Senior AI Engineer will deliver the Lendistry AI strategy. This is a hands-on applied engineering role for an experienced LLM practitioner who can take ownership of end-to-end AI features — from design through production operation — and help set technical direction for the engineers building alongside you.

You will work directly with the VP Organizational Intelligence, the AI team lead, and the Senior Staff Engineer, AI. You will lead the day-to-day delivery of agentic workflows, document intelligence, retrieval systems, and borrower- and operator-facing AI experiences, and you will help mentor more junior AI engineers on the team. You will contribute to and shape the shared AI platform — the prompt registry, tool-calling framework, evaluation harness, and inference routing layer — that every Lendistry product team consumes.

Lendistry: Who We Are

We’re proud to be the nation’s largest minority-led, tech-savvy lender for small businesses and commercial real estate. As a certified Community Development Financial Institution (CDFI) and Community Development Entity (CDE), our mission is all about creating economic opportunities and fueling growth for small business owners and their communities. Join us as we pave the way with innovative financing and financial education!

What You’ll Be Doing

As a Senior AI Engineer on the Lendistry AI team, you will lead the delivery of:

Document intelligence pipelines that read loan applications, tax returns, bank statements, and financial statements with human-level comprehension and full audit trails.

Underwriting copilots that surface risk signals, policy checks, and recommended conditions in real time for Lendistry underwriters.

Borrower-facing conversational AI that helps small business owners navigate applications, understand decisions, and manage their loans.

Shared AI platform components — prompt registry, tool-calling framework, evaluation harness, retrieval infrastructure, and the inference routing layer that every product team consumes.

The evaluation and observability layer that turns AI reliability from a hope into a measured, managed property of the system.

LLM Systems Ownership

Own end-to-end LLM features — from requirements through design, implementation, evaluation, deployment, and production operation — across origination, underwriting, servicing, and borrower experience.

Lead the design of new agentic workflows — LLMs that plan, call tools, evaluate results, and iterate across multi-step lending tasks with appropriate human-in-the-loop controls.

Maintain, debug, and improve existing LLM-powered features already running in production — prompt pipelines, retrieval systems, and the document intelligence stack.

Fine-tune and adapt foundation models (including LLaMA-family open-weight models and Bedrock-hosted models) to Lendistry-specific tasks using LoRA, QLoRA, instruction tuning, and prompt optimization techniques.

Design and build RAG systems end to end — chunking strategies, embedding model selection, vector retrieval, hybrid search, and re-ranking — tuned for financial documents and lending policy.

Agentic Workflows & Document Intelligence

Lead the development of document processing pipelines that extract structured data from PDFs, scanned images, and other unstructured financial documents using a combination of OCR, layout understanding, and LLM-based extraction.

Design validation, confidence scoring, and fallback mechanisms that make AI outputs safe to use in regulated, high-stakes financial decisions — with clear audit trails and escalation paths.

Diagnose and resolve agentic failure modes — non-determinism, prompt sensitivity, tool misuse, looping, context-window exhaustion, and retrieval gaps — and build the patterns that prevent recurrence across the team.

Platform, Evaluation & Reliability

Contribute to and shape the shared AI platform — the prompt registry, tool-calling framework, evaluation harness, retrieval infrastructure, and inference routing layer owned by the AI team.

Design evaluation frameworks that measure model quality, output reliability, retrieval accuracy, and regressions across iterations — golden sets, LLM-as-judge scoring, and human-review harnesses.

Instrument AI systems with observability — logging, metrics, traces, token and cost accounting, drift monitoring, and alerting on accuracy, latency, and failure modes.

Manage cost and latency at the feature level — token budgeting, response caching, model-tier routing, and batching strategies — treating cost as a first-class engineering constraint.

Technical Leadership & Collaboration

Partner with the AI team lead and Senior Staff Engineer, AI to translate AI strategy and architectural direction into shipped, reliable features.

Collaborate with product, credit, underwriting, and platform engineering to translate business requirements into reliable LLM system designs.

Mentor more junior AI engineers through design reviews, code reviews, and pairing — raising the bar on prompt engineering, evaluation discipline, and responsible AI development.

Lead proof-of-concept work to validate new AI use cases quickly, measure real business impact, and scale what works into production.

AI-Assisted Development Practice

Lendistry AI engineers are expected to be among the most effective users of AI tools in the company. This is how we ship.

Daily use of AI coding assistants — Claude Code, GitHub Copilot, Cursor, or equivalents — as a standard part of the development loop for code generation, refactoring, testing, documentation, and review.

Human in the Loop: Follow human review process – AI engineers must maintain clear judgment and utilize established criteria for about when to trust, verify, or override AI-generated suggestions , outputs, consistent with Lendistry’s AI usage policies and applicable regulatory requirements, particularly in security-contexts involving lending decisions, borrower data, or other sensitive and business-critical contexts and financial information.

Leadership in adopting and sharing emerging agentic development tools across Lendistry engineering.

Familiarity with agentic development concepts — multi-step task automation, LLM tool use, prompt engineering for code generation, and the integration of AI agents into engineering workflows.

Your Areas of Knowledge and Expertise

Builder mentality. Bias toward shipping production systems; pragmatic about tradeoffs between model quality, latency, and cost.

Ownership. Takes features from prototype through production, operates what you build, and owns the outcome.

Rigor. Measures quality instead of eyeballing it; builds evaluation before declaring victory.

Mentors