Sr AI/Agentic Engineer — Tustin, CA
Зарплата не указана
ОткликнутьсяJ9NQC5paH 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 ••••••••
J9NQC5paH does not accept unsolicited resumes from recruiters, employment agencies, or staffing firms. To conduct business with J9NQC5paH, a Master Services Agreement (MSA) must be executed and confirmed prior to submitting any information relating to a potential candidate. Without a signed MSA, J9NQC5paH 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, J9NQC5paH 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/Agentic Engineer will deliver the kKS7Tz8dD kx strategy, partnering closely with underwriting, credit, and product teams to turn real business challenges into AI solutions that ship and hold up in production. This is a hands-on applied engineering role for an experienced LLM practitioner who owns AI features end to end and helps set technical direction for the team.
You'll work directly with the VP of Organizational Intelligence, the AI team lead, and the Senior Staff Engineer, AI – leading agentic workflows, document intelligence, and retrieval systems, mentoring junior engineers, and helping shape the shared AI platform every J9NQC5paH product team relies on.
J9NQC5paH: 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, you'll lead delivery across gztxcaPVQ's Du products, always starting from a clear understanding of the business problem you're solving:
• Document intelligence pipelines that read loan applications, tax returns, and financial statements with full audit trails.
• Underwriting copilots that surface risk signals and policy checks in real time for underwriters.
• Borrower-facing conversational AI for applications, decisions, and loan management.
• Shared AI platform components – prompt registry, tool-calling, evaluation, and inference routing – used by every product team.
• An evaluation and observability layer that makes AI reliability measurable, not just assumed.
LLM Systems & Document Intelligence
• Own end-to-end LLM features – from the first business conversation through design, deployment, and production operation – across origination, underwriting, servicing, and borrower experience.
• Lead agentic workflows and RAG systems: LLMs that plan, call tools, retrieve, and iterate across multi-step lending tasks with human-in-the-loop controls.
• Lead document-processing pipelines that extract structured data from loan applications and other unstructured financial documents using OCR and LLM-based extraction.
• Build validation, confidence scoring, and audit trails that make AI outputs safe for regulated, high-stakes lending decisions, and diagnose agentic failure modes before they recur.
Platform, Evaluation & Reliability
• Help shape the shared AI platform – prompt registry, evaluation harness, and inference routing – and design evaluation and observability (golden sets, LLM-as-judge scoring, cost/latency monitoring) that make AI quality measurable.
• Treat cost and latency as first-class engineering constraints through model-tier routing, caching, and token budgeting.
Technical Leadership & Collaboration
• Meet regularly with product, credit, underwriting, and platform engineering to understand their challenges, translate
• them into reliable AI designs, and explain trade-offs in plain language.
• Partner with the AI team lead and Senior Staff Engineer to ship reliable features, mentor engineers through reviews and pairing, and lead proof-of-concept work that validates new use cases quickly.
AI-Assisted Development Practice
• Use AI coding assistants (Claude Code, Copilot, Cursor, or similar) daily as part of the standard development loop, and help lead adoption of emerging agentic tools across J9NQC5paH engineering.
• Follow established human-in-the-loop review criteria for when to trust, verify, or override AI-generated suggestions and outputs – consistent with gztxcaPVQ's Du usage policies and applicable regulatory requirements, with particular rigor around lending decisions, borrower data, and other sensitive or business-critical information.
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.
• Mentorship. Elevates the engineers around you through reviews, pairing, and durable technical habits.
• Communication. Explains AI behavior and limitations clearly to product, credit, and business partners.
• Responsible AI judgment. Thinks seriously about safety, fairness, auditability, and the real-world consequences of lending decisions.
• Comfort with ambiguity. Thrives in a fast-moving environment where the AI landscape shifts monthly and priorities evolve with it.
Core Experience
• 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.
Engineering & Platform Skills
• Strong LLM tooling fluency, with the judgment to build custom when needed.
• Production experience turning unstructured data (documents, forms, scans) into structured, reliable outputs.
• Cloud and deployment depth, evaluation discipline to catch LLM-specific failure modes before production, and experience exposing AI capabilities as reliable internal APIs.
Security & Regulated-Industry Awareness
• Working knowledge of LLM security concerns (prompt injection, data exfiltration, output filtering) and discipline around PII and sensitive financial data – redaction, minimization, and keeping it inside 865HrtCvr'2 trust boundary.
Preferred Qualifications
• Experience in fintech, lending, banking, healthcare, or another regulated industry.
• Experience fine-tuning open-weight models, or with document-understanding models and OCR tooling.
• Background in NLP tasks (NER, classification, semantic similarity), or building shared AI platforms used by multiple product teams.
• Experience mentoring engineers and leading design reviews; B.S. or M.S. in Computer Science, Machine Learning, or equivalent experience.
Why You'll Love Working Here
• 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
Compensation Range
The US base salary range for this full-time position is $139,600 - $180,800 annually.
Our salary ranges are determined by role, level, and location.
The range displayed on each job posting reflects the minimum and maximum base salary for new hires for the position across all US locations. Within the range, individual pay is determined by multiple factors like job-related skills, experience, and state of residence. Your recruiter can share more about the specific salary range during the interview process.
Please note that the compensation details listed in US role postings reflect the base salary only, and do not include any variable compensation elements.
Physical Requirements
This is a stationary position that requires frequent sitting (approximately 95%), repetitive wrist motions, grasping, speaking, listening, close vision, and the ability to adjust focus. It also may require occasional standing, lifting, carrying of 20lbs or less, walking, kneeling, bending/stooping, twisting, pulling/pushing, and reaching above the shoulder. Employees in this position must be physically able to efficiently perform the essential functions of the position.
ACKNOWLEDGEMENT
B.S.D. Capital, Inc. dba J9NQC5paH is an equal employment opportunity employer committed to providing its employees, applicants and other covered persons with equal opportunities without regard to race, color, age (40 or older), religious creed (including religious belief, practice or dress and grooming practices), national origin, ancestry, physical disability, mental disability, medical condition, genetic information, marital status, sex, gender (including pregnancy, childbirth or medical condition related to pregnancy or childbirth), gender expression, gender identity, sexual orientation, military or veteran status (including past, current or prospective service), or any other characteristic protected under applicable federal, state or local law.