Staff Applied AI Researcher, Agentic Search

Job not on LinkedIn

🔥 0 minutes ago

🌐 Netherlands, United Kingdom, +1 more countries – Remote

🇳🇱 Netherlands – Remote 🇬🇧 United Kingdom – Remote 🇨🇭 Switzerland – Remote

⏰ Full Time

🔴 Lead

🧠 AI Research Scientist

👻 Ghost score 10%

What it means: the chance that no one is really hiring for this job.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Tavily

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2024

🔌 API

🤖 Artificial Intelligence

☁️ SaaS

💰 $20M Series A - Tavily on 2025-08

API • Artificial Intelligence • SaaS

Tavily is a company that provides a secure API for connecting AI agents to the web, offering real-time web access, search, extraction, crawling, and research endpoints. The platform grounds models with fresh web context by retrieving live web data, extracting and structuring content, and chunking it for models to prevent hallucinations. Tavily emphasizes production-grade performance: low latency (180 ms p50), high availability (99. 99% SLA), scalability (300M+ monthly requests, billions of pages crawled), intelligent caching and indexing, and built-in safeguards for security, privacy, and content validation (blocking PII leakage, prompt injection, malicious sources). It integrates with leading LLM providers (OpenAI, Anthropic, Groq), is aimed at developers and enterprises, and is used for real-time AI search, retrieval for agents, and research. The company offers docs, SDKs, pricing, events, and partnerships with major platforms, and targets building the web access layer for AI agents.

📋 Description

• Design an agent-native search system for low-latency single-hop and complex deep-search tasks involving iterative planning, querying, refinement and reasoning • Train ranking and retrieval models optimized for agent-driven workflows under real-world constraints • Bring advances from the research community into the search stack and ship them to production • Drive applied research and technical direction across retrieval and ranking systems • Design and evolve multi-stage retrieval architectures including query understanding, rewriting, retrieval, reranking and iterative retrieval • Lead experimentation with embedding research, sparse and hybrid retrieval, reranking and context compression • Develop methods for grounding LLMs in real-time web data at scale using trust, quality and freshness signals • Partner with the evaluation team to define metrics for agentic systems • Analyze relevance, latency and cost trade-offs and work with engineering to deploy web-scale systems • Mentor researchers and engineers and raise the team's technical bar • Own a specific part of the search stack in the first year, such as ranking or iterative retrieval

🎯 Requirements

• 8+ years of experience in applied AI, ML, or software engineering • Proven track record of shipping ML or AI systems to production at scale • Deep experience with search, retrieval, ranking or building RAG-based assistants • Strong understanding of modern deep learning, especially transformers and embeddings • Experience with LLM-integrated or knowledge-intensive systems • Experience designing evaluation frameworks and metrics for ML systems • Strong programming skills in Python • Top-tier publications (ICLR, ICML, NeurIPS, AAAI, EMNLP, ACL) • Ability to operate in a fast-moving, product-driven environment with high ownership and autonomy • Nice to have: Background in agentic AI systems (agents, tool use, autonomous workflows) • Nice to have: Experience with RL post-training of LLMs or VLMs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume