Senior Software Engineer - AI Innovation
Does Worth AI sponsor H-1B visas?
Check real filing data, salaries & approval rates on VisaTalentUSA
Job Description
Remote AI and machine learning roles on HireSkys range from AI engineering and NLP to computer vision and prompt engineering. Listings usually name their frameworks and models — match them against your own hands-on work before applying.
Key Skills Required
Master these to land this role
Want to know if you're a match for this job?
Worth AI, a leader in AI onboarding and underwriting, is seeking a Senior Software Engineer - AI Innovation to join their team. Their mission is to revolutionize decision-making with artificial intelligence, helping fintechs, lenders, payment processors, and financial institutions onboard small businesses faster, smarter, and more confidently. They are building the infrastructure that powers real-time KYB, KYC/IDV, underwriting, and continuous risk monitoring at enterprise scale, including the Worth Score™, a unified credit score derived from 1,200+ data points across 700M+ SMBs.
As a Senior Software Engineer - AI Innovation, you will design and ship production agent systems that make consequential decisions on regulated financial data. Worth’s platform consolidates onboarding and underwriting into a single AI-powered system, with agents that read, reason over, and act on high-stakes signals. You will own the end-to-end lifecycle: architecting agent graphs, building retrieval and tool layers, instrumenting with evaluations and observability, and deploying against SOC 2 / GDPR / CCPA guardrails. You will partner closely with the Chief AI Officer, applied scientists, product, and platform teams to turn agentic patterns into customer outcomes.
Responsibilities
- Design and ship multi-step agentic systems (planner/executor, tool-using, multi-agent, human-in-the-loop) that automate KYB, underwriting, case review, and risk monitoring workflows.
- Architect agent graphs in LangGraph (or comparable frameworks like CrewAI, AutoGen, Claude Agent SDK) with explicit state, durable execution, retries, and safe fallbacks.
- Build and harden the retrieval layer powering agents, including chunking strategies, hybrid search, reranking, and grounded citation across SoS filings, IRS records, bank data, and Worth’s 700M+ SMB graph.
- Own the evaluation stack: golden sets, offline regression suites, LLM-as-judge, online A/B and shadow evaluations, and red-teaming for jailbreaks, prompt injection, and PII leakage.
- Integrate agents into Worth’s production systems via well-typed tools, MCP servers, and existing services (decisioning engine, case management, crosswalking). Treat tool surface area as a product.
- Drive production MLOps for agents, including deployment, versioning, traffic shaping, cost/latency budgets, observability (traces, token spend, tool call success), and on-call playbooks for agent incidents.
- Partner with security, compliance, and legal to ensure agents adhere to SOC 2, GDPR, CCPA, and fair-lending postures from day one.
- Translate ambiguous product bets into concrete agent designs, prototypes, and shipped features.
- Mentor engineers across the organization on agent patterns, prompt engineering hygiene, evaluation discipline, and failure modes of LLM systems.
- Stay ahead of frontier models, frameworks, and patterns, and bring proven solutions to production.
Technology Stack
- Languages & Runtimes: Python, Node.js, TypeScript
- Agent / LLM frameworks: LangGraph, LangChain, Claude Agent SDK, MCP, OpenAI SDK
- Models: Anthropic Claude, OpenAI, open-weight (Llama, Mistral) where appropriate
- Retrieval & Data: PostgreSQL, pgvector / vector DBs, OpenSearch, Kafka, Redshift, Redis
- Infra & Orchestration: AWS, Kubernetes (EKS), ArgoCD, Terraform
- Evals & Observability: LangSmith / Langfuse / Braintrust-style tooling, Datadog, custom eval harnesses
Requirements
- 8+ years of professional software engineering experience, with at least 2 years building production LLM or agentic systems (not just notebooks or demos).
- Solid software engineering experience in front-end, APIs, async patterns, queues, databases, and distributed systems.
- Demonstrated ownership of major features or subsystems in production.
- Demonstrated experience mentoring junior engineers and raising team quality standards.
- Experience with event-driven systems: enrichment, retries, dead-lettering, backpressure.
- Experience managing containerized applications in Kubernetes, EKS, ArgoCD, operators, Kustomize.
- Deep, hands-on experience with at least one modern agent framework (LangGraph strongly preferred) and a track record of shipping agents that run, fail gracefully, and recover.
- Real experience with evaluations, including building golden sets, running offline and online evaluations, and making ship/no-ship calls.
- Production MLOps fluency: deploying LLM workloads under real latency, cost, and reliability constraints, and instrumenting what you ship.
- Strong proficiency in Python; comfortable in TypeScript / Node.js for integrating with Worth’s services.
- Clear, calibrated communicator able to explain agent trade-offs to product, security, and customers without hand-waving.
- Operates with extreme ownership in ambiguous, fast-moving environments. Excited to work alongside a team that values “One Team”, “Extreme Ownership”, and “Create Raving Fans.”
Success Metrics
- Agent Quality: Measurable improvements in task success rate, grounding accuracy, and hallucination rate on Worth’s eval suites, tied to customer-visible outcomes.
- Production Reliability: Agents meet defined SLOs for latency (P90/P99), tool-call success rate, and cost per task.
- Velocity: New agent capabilities go from prototype to production in weeks, not quarters, without skipping evaluations or guardrails.
- Risk Posture: Zero material incidents tied to prompt injection, PII leakage, or unsafe tool use on agents owned.
- Force Multiplier: Patterns, tools, and evaluation scaffolding built are adopted by other engineers across Worth.
Bonus Points (nice to haves, not requirements)
- Prior experience in fintech, lending, payments, KYB/KYC, fraud, or AML — or any other regulated, high-stakes data domain.
- Experience building MCP servers or other structured tool interfaces for LLMs.
- Background in classical ML (ranking, scoring, calibration) applicable alongside LLM systems.
- Experience designing explainable / auditable AI workflows for regulated environments (SOC 2, model risk management, fair lending).
- Open-source contributions to agent frameworks, evaluation tooling, or retrieval libraries.
- Hands-on AWS depth (EKS, MSK, RDS, S3, Lambda) and IaC with Terraform.
All remote hires will be required to travel to Orlando, Florida at least twice per year for Town Halls and team collaboration, in addition to orientation in Orlando, Florida.
Benefits
- Health Care Plan (Medical, Dental & Vision)
- Retirement Plan (401k, IRA)
- Life Insurance
- Flexible Paid Time Off
- 9 Paid Holidays
- Family Leave
- Remote
- Hybrid work (for Orlando Associates)
- Free Food & Snacks (Orlando)
- Wellness Resources
How would you rate this job post?
See what other professionals think about this role.
How applying works on HireSkys
- 1.Click Apply. You go to the application — the employer's own page or form, or the HireSkys apply flow — and submit your profile as the employer asks.
- 2.The employer reviews. Shortlisting is done by the employer, not by HireSkys, so the timeline and next steps come from them.
- 3.Hear back directly. If shortlisted, the employer contacts you directly. Applying through HireSkys is free for jobseekers — never pay for a job application.
Similar Opportunities
Computer Vision Engineer
Augmodo
United StatesAI & Machine Learning Intern Program (Autonomy Team)
Stackav
Panama
United StatesApplied Researchers (Senior+) - Gaussian Splatting & Radiance Fields
Miris
United StatesCreative Community & Marketplace Lead (AI Video & Motion)
OpusClip
United StatesMore Openings at Worth AI
Explore Top Companies in this Space
Ignition
SaaS / Financial Technology / Professional Services / Automation
StarCompliance
Enterprise Software / Financial Services / Compliance Technology / SaaS
Termgrid
Financial Technology (FinTech) & Investment SaaS / Private Equity & Credit Markets Operating Infrastructure / Capital Structure Management & Deal Execution Automation
Trading 212
FinTech & Wealth Management / Retail Brokerage & Trading Apps / Commission-Free Investing SaaS / Financial Technology Platforms
Worth AI
View Company ProfileWorth AI (operating via worthai.com) is a premier AI-powered onboarding and underwriting workflow automation platform engineered to accelerate approvals, strengthen compliance, and optimize risk management for financial institutions. Founded in 2023 and headquartered in Orlando, Florida, the enterprise fundamentally transforms how lenders, credit unions, fintechs, and payment processors manage SMB (Small and Medium-sized Business) onboarding. Moving far beyond traditional, fragmented manual reviews and siloed data systems, Worth natively unifies predictive risk monitoring, custom rules-based decisioning, and automated KYB/KYC compliance into a single, cohesive ecosystem. The platform empowers organizations to seamlessly process applications with extreme accuracy, significantly reducing abandonment rates while increasing approval speed. Under the hood, their proprietary Crosswalking Technology leverages a massive database of over 350 million SMBs—synthesizing identity, financial, and behavioral signals from dozens of sources to deliver real-time, confidence-weighted risk assessments via the Worth Score™. Capturing massive industry momentum with over $50 million in total funding from investors like TTV Capital and Fulcrum Equity Partners, Worth AI remains a definitive cornerstone of the modern financial technology landscape, ensuring equitable access to credit and frictionless business onboarding at enterprise scale.
Safety First
- Never pay for a job application.
- Do not share sensitive bank info.
- Verify the client before starting work.