Senior AI Engineer, Agentic Data Enrichment
Senior AI Engineer responsible for production LLM agents that enrich business identity data through web discovery, verification, classification, and risk scoring. The role requires strong asynchronous Python, agent and evaluation expertise, browser automation, and experience operating AI systems in production.
About the job
Responsibilities
- Own industry and category classification of businesses using heterogeneous signals such as names, websites, directories, and reviews.
- Build and maintain systems that discover and verify a business’s 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/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 responsibility.
- Strong asynchronous Python, structured-data libraries, modern web frameworks, and relational databases.
- Experience with multiple frontier LLM providers and at least one agent framework.
- Experience developing evaluation methodology, including curated golden datasets, scoring functions, labeling guidelines, and regression diagnostics.
- Browser automation experience, including headless browsers, anti-bot evasion, and authenticated flows.
- Knowledge of structured-output approaches, including JSON Schema mode, function calling, and text extractors.
Nice to Have
- Web scraping at scale, residential proxies, request fingerprinting, CDN defeats, and authenticated flows.
- Evaluation frameworks such as LangSmith, Braintrust, or Evals.
- Entity resolution, record linkage, and fuzzy matching at scale.
- Browser automation using the DevTools Protocol.
- Tool registry or toolset abstractions spanning multiple LLM providers.
- Cost and latency optimization, including response caching, semantic caching, model routing, thinking-budget tuning, and prompt-cache optimization.
Compensation and Benefits
- Salary: $230,000–$340,000 annually, plus equity.
- Flexible paid time off.
- 100% company-paid health, dental, and vision premiums.
- 401(k) with company match.
- HSA contributions on applicable plans.
- $250 monthly gym stipend.
- Hybrid schedule with four days per week in the office.
Skills
Python, Async Python, Relational Databases, Web Frameworks, Llm Agents, Agent Frameworks, Browser Automation, Web Scraping, Json Schema, Function Calling, Entity Resolution, Fuzzy Matching, Langsmith, Braintrust, Devtools Protocol
Similar jobs
ML Engineering jobs
Otter
Mountain View, CA
Leads the development and production deployment of large-scale ASR and TTS systems for conversational intelligence products. The role requires 5+ years of industry experience, deep speech-model expertise, and strong software engineering and ML operations capabilities.
Ambience Healthcare
San Francisco, CA
Build and improve production AI systems for clinical products, owning evaluations, model behavior, agentic workflows, data flywheels, deployment, and observability. The role requires 5+ years of production ML or applied AI experience, strong Python and modern ML framework skills, and hands-on debugging expertise.
Dialpad
United States
Leads development of speech models, decoders, and low-latency inference systems for next-generation voice agents. Requires 5+ years in speech ML or related audio AI, strong Python and PyTorch experience, and the ability to guide technical direction and mentor engineers.
Ontario, Canada
Design, build, and deploy production ML systems for recommendations, search, ranking, and advertising at internet scale. Own the full ML lifecycle from modeling to monitoring with strong cross-functional collaboration.
Fetch
United States
Build and operate low-latency machine learning systems for ad ranking, relevance, and optimization, including feature pipelines, experimentation, evaluation, and production inference. The role requires 6+ years of software engineering experience, strong Python skills, AWS experience, and practical LLM application experience.