SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Baselayer is rebuilding the identity and trust layer for financial institutions across the United States. The company has built the most complete business graph in America, fusing public records, IRS data, sanctions lists, web signals, and fraud telemetry from 2,200+ financial institutions to resolve any business and the humans behind it in milliseconds. Baselayer is trusted by over 20% of financial institutions in America and is expanding into gig platforms, marketplaces, AI companies, and commerce infrastructure.
You will join a small, high-ownership team solving real-time entity resolution at scale. The technical problems are deep: graph AI, retrieval systems, and fraud modeling stacked together. The team operates with minimal process—ideas ship quickly, and the infrastructure you build becomes load-bearing for businesses.
As Senior AI Engineer for Agentic Data Enrichment, you will own a slice of the enrichment surface end-to-end. Your responsibilities include:
- Own industry and category classification of businesses from heterogeneous signals (name, website, directory presence, reviews).
- Build and maintain discovery and verification systems for a business's real web presence, filtering aggregators, parked domains, brand collisions, and impersonators.
- Link individuals to businesses via public web evidence (e.g., confirming named officers or employees genuinely work there).
- Develop risk and legitimacy scoring derived from web-presence signals, fed back into downstream underwriting.
- Build and evolve shared agent infrastructure: provider-agnostic base agents, shared toolset registry (browser navigation, search, scraping, structured database lookups, scoring), eval harness, and instrumentation surface for token-and-tool tracing.
- Own model selection, agent design, prompt and tool engineering, eval methodology, and cost control across your enrichment surface.
You will use LLM-driven agents that crawl, click, search, and extract structured evidence from across the web, treating this as a production data pipeline rather than a research demo.
Minimum requirements: shipped LLM-driven agents to production (not notebooks or demos); strong async Python including structured-data libraries, modern web frameworks, and relational databases; experience across multiple frontier LLM providers and at least one agent framework with deep knowledge of failure modes; built or maintained eval methodology with curated golden datasets, scoring functions, and labeling guidelines; browser automation experience including headless browsers, anti-bot evasion, and authenticated flows; informed opinions on structured-output reliability (JSON-schema mode vs. function calling vs. extractor-on-top-of-text).
What sets you apart: web scraping at scale (anti-bot evasion, residential proxies, request fingerprinting, authenticated flows, CDN defeats); eval-framework experience (LangSmith, Braintrust, Evals, or custom); entity resolution, record linkage, or fuzzy matching at scale; browser-automation experience at the devtools-protocol level; built a tool registry or toolset abstraction over multiple LLM providers; cost and latency optimization experience.
