Forward-Deployed AI Engineer
Saaf Finance
IndiaremotePosted 1 month ago
Skill Required
Forward-Deployed-AI-EngineerForward-Deployed-ML-EngineerForward-Deployed-AI-EngineeringForward-Deployed-EngineerForward-Deployed-Software-EngineerSenior-Forward-Deployed-EngineerAI-EngineerAI EngineerAIData StructuresSystem DesignEngineeringautomationObservabilitysimilar)buildingfintechPythondesignCloudjQueryAPIsSassRAGAWSandGenerative AIGoMachine LearningFulltime
Key highlights
- Competitive compensation
- Unlimited PTO
- Remote‑first with flexible hours
- $2,000/year professional development budget
- Must have shipped LLM‑powered features or agents to production
- Strong Python and LLM tooling fluency required
Role overview
Saaf AI is hiring a Forward‑Deployed AI Engineer to design, build, and ship end‑to‑end AI‑powered products and agents that transform mortgage lending. The engineer will own the full lifecycle from a business problem to a production AI system, working on automating underwriting decisions, document intelligence, borrower‑facing experiences, and AI evaluation and quality systems.
Responsibilities
- Design and ship AI‑powered agents that automate or accelerate mortgage lending workflows, including condition management, document review, borrower communication, and underwriting analysis.
- Build multi‑step LLM agents that can navigate loan files, evaluate conditions, flag exceptions, and surface recommendations to underwriters.
- Design agentic workflows with tool use, structured output, memory, and human‑in‑the‑loop checkpoints.
- Integrate AI agents with internal systems, external data sources, and third‑party APIs to close the loop between insight and action.
- Extend and improve document extraction pipelines for income documents, appraisals, title, and more using the latest extraction and classification models.
- Build retrieval‑augmented systems that let underwriters and borrowers query complex loan files in natural language.
- Design feedback mechanisms that use reviewer corrections to improve extraction accuracy over time.
- Build AI‑generated task lists and smart checklists that adapt to each borrower’s loan scenario.
- Create intelligent routing and prioritization to determine which loans need attention, which borrowers are at risk of drop‑off, and which conditions are blockers.
- Design conversational AI experiences that guide borrowers through complex decisions without requiring a loan officer on every interaction.
- Build evaluation frameworks that measure AI output quality against ground truth, not just latency.
- Design human review workflows for low‑confidence AI outputs and use those reviews to create labeled training data.
- Monitor production AI performance—including accuracy, coverage, and failure modes—and iterate relentlessly.
- Own end‑to‑end feature development: requirements, design, implementation, deployment, and monitoring.
Requirements
- Proven experience shipping LLM‑powered features or agents to production, handling real‑world challenges such as latency, hallucination, evaluation, prompt regression, and retrieval quality.
- Strong Python programming skills; ability to write clean, production‑quality code, including async, APIs, and complex data structures.
- Fluency with major LLM APIs and at least one agent orchestration framework; practical knowledge of structured output, tool calling, retrieval‑augmented generation, and evaluation.
- Product thinking: ability to translate a business process into an AI system design with a user‑centric focus.
- Demonstrated ownership of features from requirements through design, implementation, deployment, and monitoring without handing off hard parts to other teams.
- Ability to iterate quickly: ship early, measure, and improve with short feedback loops.
Nice to have
- Experience in fintech, lending, insurance, or other regulated industries.
- Full‑stack experience, comfortable building lightweight UIs, APIs, or internal tools as needed.
- Cloud deployment experience, preferably AWS, including containerization, deployment, and operation of systems.
- Experience with document understanding technologies such as OCR, extraction models, and converting unstructured sources to structured data.
- Background in building human‑in‑the‑loop systems, including review workflows, feedback capture, and data‑flywheel design.
- Experience with mortgage or real‑estate data.
- Familiarity with workflow automation tools like n8n or similar.
- Exposure to fine‑tuning or model adaptation for domain‑specific tasks.
- Experience building AI products that handle PII and comply with regulatory requirements such as FCRA and GLBA.
Benefits
- Competitive compensation
- Unlimited PTO
- Remote‑first with flexible hours
- $2,000/year professional development budget
- Home office setup stipend
Additional details
- AHL + Saaf AI — Mortgage Lending, Reimagined
- Saaf AI is part of American Heritage Lending, a top‑10 private lender processing billions in loan volume with 15+ years of growth.
- Backed by some of the largest asset managers and funds; company is growing fast.
- The company deploys AI across underwriting, document processing, and borrower experience; AI is a core building material.
- The role is not an ML research or prompt‑engineering sandbox; it is a hands‑on builder role owning the full arc from business problem to working AI system in production.
- Mortgage lending is one of the last industries to be meaningfully transformed by AI; problems are hard, data is rich, stakes are real.
- AI‑first culture: every engineer uses AI to build AI (Claude Code, agentic workflows, AI‑assisted code review).
- Direct impact on a $2 trillion industry; work affects every loan processed, speeding underwriting and reducing paperwork.
- Originally posted on Himalayas