Skip to content
BaselayerBaselayerSan Francisco, CA

Senior AI Engineer, Agentic Data Enrichment

Build and own production LLM-driven agents that enrich business identities using web discovery, evidence extraction, classification, and risk signals. The role requires strong asynchronous Python, browser automation, multi-provider LLM experience, evaluation methodology, and production agent ownership.

230k – 340k/yr
Hybrid5+ YOEML Engineering

About the role

Responsibilities

  • Own industry and category classification of businesses from heterogeneous signals, including names, websites, directory presence, and reviews.
  • Build and maintain discovery and verification systems for businesses' real web presence, filtering aggregators, parked domains, brand collisions, and impersonators.
  • Link individuals to businesses using public web evidence.
  • Develop risk and legitimacy scoring from web-presence signals for downstream underwriting.
  • Build and evolve shared agent infrastructure, including provider-agnostic base agents, tool registries, evaluation harnesses, and token-and-tool tracing instrumentation.
  • Own model selection, agent design, prompt and tool engineering, evaluation methodology, and cost control.

Requirements

  • Production experience shipping LLM-driven agents with real users, costs, failure modes, and on-call responsibilities.
  • Strong asynchronous Python experience with structured-data libraries, modern web frameworks, and relational databases.
  • Experience with multiple frontier LLM providers and at least one agent framework.
  • Experience building or maintaining evaluation methodology, including golden datasets, scoring functions, labeling guidelines, and regression diagnostics.
  • Browser automation experience with headless browsers, anti-bot evasion, and authenticated flows.
  • Strong understanding of structured-output reliability, including JSON Schema mode, function calling, and text extraction.

Nice-to-Haves

  • Web scraping at scale, including residential proxies, request fingerprinting, authenticated flows, and CDN defeats.
  • Evaluation frameworks such as LangSmith, Braintrust, Evals, or custom systems.
  • Entity resolution, record linkage, or fuzzy matching at scale.
  • Browser automation at the DevTools Protocol level.
  • Tool registry or toolset abstraction experience across multiple LLM providers.
  • Cost and latency optimization through response caching, semantic caching, model routing, thinking-budget tuning, and prompt-cache optimization.

Compensation and Benefits

  • Salary: $230,000–$340,000 plus equity.
  • Flexible PTO.
  • 100% company-paid health, dental, and vision premiums.
  • 401(k) with company match.
  • HSA contributions on applicable plans.
  • $250 monthly gym stipend.

Skills

Pythonllm agentsAgent FrameworksLLMsweb frameworksRelational Databasesbrowser automationheadless browsersweb scrapinganti-bot evasionentity resolutionfuzzy matchingjson schemafunction callinglangsmith

Similar roles

ML Engineering jobs
OpenAI

Applied AI Engineer, GTM Growth Engineering

OpenAISan Francisco, CA

Build and improve production AI agent systems for OpenAI's GTM workflows. Own the end-to-end improvement loop using feedback, evaluation, experimentation and backend services to drive measurable gains in customer engagement, pipeline and team productivity. Requires 4+ years building reliable LLM-powered production systems plus strong product judgment.

230k – 385k/yrOn-site7+ YOEML Engineering
Instabase

AI Engineer

InstabaseSan Francisco, CA

Staff AI Engineer building the Agent Harness runtime for Instabase's SuperApp: design secure sandboxed execution environments, state machines for agent orchestration, tool-calling frameworks, and guardrails connecting LLMs to production systems. Requires 8+ years distributed systems experience plus agentic AI expertise.

230k – 315k/yrHybrid8+ YOEML Engineering
Instabase

Technical Lead Manager

InstabaseSan Francisco, CA

Player-coach Technical Lead Manager for AI Systems & Agents at Instabase. Hands-on architect and builder of stateful multi-turn agent loops, secure code execution sandboxes, tool orchestration via MCP, and evaluation harnesses while leading and growing a small elite team of AI engineers.

230k – 270k/yrHybrid8+ YOEML Engineering
Otter

Senior Machine Learning Engineer

OtterMountain View, CA

Lead projects building and deploying large-scale ASR, NLP, and LLM systems for meeting intelligence. Requires 5+ years building production ML systems with PyTorch/JAX and experience with speech/language models.

230k – 265k/yrHybrid5+ YOEML Engineering
Cohere

Senior Research Engineer - Safety Tooling and Data

CohereNew York, NY

Senior Research Engineer building data synthesis, analysis, and management tooling for AI safety model training and evaluation. Requires strong software engineering, statistics, and ML framework expertise.

230k – 380k/yrRemote5+ YOEML Engineering