[Remote] Sr AI/Agentic Engineer

Note: The job is a remote job and is open to candidates in USA. Lendistry is the nation’s largest minority-led, tech-savvy lender for small businesses and commercial real estate. The Senior AI Engineer will lead the delivery of AI strategies, focusing on document intelligence, agentic workflows, and mentoring junior engineers while shaping the shared AI platform for the company.

Responsibilities

• Deliver the Lendistry AI strategy
• Lead the day-to-day delivery of agentic workflows, document intelligence, retrieval systems, and borrower- and operator-facing AI experiences
• Contribute to and shape the shared AI platform — the prompt registry, tool-calling framework, evaluation harness, and inference routing layer
• Own end-to-end LLM features — from requirements through design, implementation, evaluation, deployment, and production operation
• 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
• 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
• 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
• 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
• 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
• 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

Skills

• 5+ years of software engineering experience, with 3+ years building and shipping LLM-powered applications in production
• Expert-level Python for production systems — clean architecture, type-safe data modeling (Pydantic or equivalent), clean async patterns, and testable design
• Deep hands-on production experience with at least one major LLM provider — AWS Bedrock, Anthropic Claude, OpenAI GPT, Google Gemini, or equivalent — including tool/function calling, structured output, and streaming
• Proven track record designing and operating RAG systems end to end — chunking, embeddings, vector databases (Qdrant, Pinecone, Weaviate, OpenSearch, or pgvector), retrieval, and re-ranking — including measuring and improving retrieval quality
• Demonstrated experience leading agentic workflows in production — LLM agents that call tools, reason across multiple steps, and autonomously complete multi-stage tasks with appropriate safeguards and audit trails
• Hands-on experience with fine-tuning and adaptation — LoRA, QLoRA, instruction tuning, or preference tuning — and with rigorous evaluation of model outputs rather than demo-driven validation
• Strong LLM tooling fluency — LangChain or LangGraph, LlamaIndex, DSPy, Hugging Face — with the judgment to pick the right tool and the willingness to build custom when the tool is wrong
• Production experience with unstructured data — extracting, classifying, and generating structured outputs from text-heavy inputs, including documents, forms, and scanned images
• Cloud and deployment depth — AWS preferred (including Bedrock), containerization (Docker), and hands-on experience with self-hosted LLM serving (vLLM, TGI, Ollama, or similar)
• Evaluation discipline — ability to design evaluation frameworks for non-deterministic systems, build golden sets, and reason about output quality at scale
• Strong debugging instincts for LLM-specific failure modes — hallucinations, retrieval gaps, prompt drift, latency spikes, and cost regressions
• API and service design experience — exposing AI capabilities as reliable internal APIs with clear contracts, error handling, and cost controls
• Working knowledge of LLM security concerns — prompt injection, data exfiltration, output filtering, and secure inference for sensitive workloads
• Discipline around PII and sensitive financial data — PII detection and redaction, data minimization, and deployment patterns that keep sensitive data inside Lendistry's trust boundary
• Experience in fintech, lending, banking, healthcare, or another regulated or data-sensitive industry
• Experience fine-tuning LLaMA or similar open-weight models on domain-specific corpora
• Familiarity with document understanding models (LayoutLM, Donut, Nougat) and modern OCR tooling (Textract, Tesseract, or equivalents)
• Background in NLP tasks such as named entity recognition, classification, or semantic similarity
• Experience building and operating shared AI platforms (prompt registry, evaluation harness, routing layer) consumed by multiple product teams
• Experience mentoring engineers and leading design reviews
• B.S. or M.S. in Computer Science, Machine Learning, or equivalent experience

Benefits

• Comprehensive Medical, Dental, and Vision Insurance
• Generous Paid Time Off
• Birthday Day Off
• 12 Paid Company Holidays
• 401(k) Match
• FSA and HSA
• Paid Life Insurance
• Paid Disability Insurance
• Pet Insurance
• Employee Assistance Program (EAP)
• Professional Development Courses
• In Office Provided Snacks and Drinks
• Gym Facilities (LA & Tustin/CEC Offices)
• In Office Engagement Activities

Company Overview

Company H1B Sponsorship