BlueCard Jobs
← Back to jobs

Staff Applied AI Researcher (Agentic Search)

Tavily

Blue Card status unknown

Location

Germany

Salary

Not disclosed

Posted

15 days ago

Language

🇬🇧 English✓ verified

Work mode

hybrid

Relocation

Not mentioned

Skills

JavaPythonDevOpsData Engineering

Job description

<p> </p> <p data-renderer-start-pos="758" data-local-id="349f5d1d97ae">We are seeking a Staff Applied AI Researcher to join a fast-growing team building an agent-native search platform - the web access layer for AI systems.</p> <p data-renderer-start-pos="912" data-local-id="52da8de25c65">You can think of this as Google search, but for AI agents: a system designed for machines, not humans. We are building agentic search, where AI systems actively plan, retrieve, evaluate, and refine information rather than simply returning results. As AI becomes the primary interface to the web, this layer will replace the role of traditional search engines.</p> <p data-renderer-start-pos="1273" data-local-id="8ba2f733eb98">We are designing these systems to search and reason over web data in real time, under strict latency and reliability constraints. This means solving retrieval, ranking and passage extraction under entirely new access patterns and at significant scale, with systems operating over constantly changing, unstructured data and serving tens of thousands of production workloads 24/7.</p> <p data-renderer-start-pos="1653" data-local-id="dc8aefa0b2c5">This role comes with ownership over key parts of our applied AI research direction and system design, with a strong expectation of defining new approaches and shipping measurable impact in production. In the first year, you will own a specific part of the search stack, e.g. ranking or iterative retrieval.</p> <p data-renderer-start-pos="1961" data-local-id="3a68defafc73"><strong data-renderer-mark="true">What you'll work on:</strong></p> <ul class="ak-ul" data-local-id="b2d49ed7-2072-4623-afb5-0f3e46fb9eff" data-indent-level="1"> <li> <p data-renderer-start-pos="1985" data-local-id="dbde4a36f318">Designing an agent-native search system that handles everything from low-latency single-hop search to complex deep search tasks requiring iterative planning, querying, refinement and reasoning.</p> </li> <li> <p data-renderer-start-pos="2182" data-local-id="330562c2b43d">Training ranking and retrieval models optimized for agent-driven workflows under real world constraints</p> </li> <li> <p data-renderer-start-pos="2289" data-local-id="a80b20c7f5e2">Bringing the latest advances from the research community to our search stack and ship it to production.</p> </li> </ul> <p data-renderer-start-pos="2396" data-local-id="c5f3d6d01f8e"><strong data-renderer-mark="true">Your responsibilities:</strong></p> <ul class="ak-ul" data-local-id="ca556365-56d6-4b18-a6ab-e96d32aada2a" data-indent-level="1"> <li> <p data-renderer-start-pos="2422" data-local-id="ba12fa15e8c5">Drive applied research and technical direction across retrieval and ranking systems</p> </li> <li> <p data-renderer-start-pos="2509" data-local-id="0ac01c95d3f6">Design and evolve multi-stage retrieval architectures (query understanding, rewriting, retrieval, reranking and iterative retrieval)</p> </li> <li> <p data-renderer-start-pos="2645" data-local-id="bdd93b58a974">Lead experimentation on modern retrieval approaches (embedding research, sparse and hybrid retrieval, reranking, context compression) and bring them into production</p> </li> <li> <p data-renderer-start-pos="2813" data-local-id="5d99bb2639e8">Develop methods for grounding LLMs in real-time web data at scale, using trust, quality and freshness signals to surface reliable sources</p> </li> <li> <p data-renderer-start-pos="2954" data-local-id="5b539cf905a3">Partner with the evaluation team to define new metrics for agentic systems, where correctness is not reducible to clicks</p> </li> <li> <p data-renderer-start-pos="3078" data-local-id="7f6ed1a6999b">Analyze trade-offs across relevance, latency, and cost, and work closely with engineering to deploy systems that operate at web scale</p> </li> <li> <p data-renderer-start-pos="3215" data-local-id="98cbe59fe7ce">Mentor researchers and engineers and help raise the technical bar of the team</p> </li> </ul> <p data-renderer-start-pos="3296" data-local-id="4e7298218846"><strong data-renderer-mark="true">Must haves:</strong></p> <ul class="ak-ul" data-local-id="288927ca-3161-4538-89a9-be6a7978542a" data-indent-level="1"> <li> <p data-renderer-start-pos="3311" data-local-id="3c107fbda2c8">8+ years of experience in applied AI, ML, or software engineering</p> </li> <li> <p data-renderer-start-pos="3380" data-local-id="529c36f68cf3">Proven track record of shipping ML or AI systems to production at scale</p> </li> <li> <p data-renderer-start-pos="3455" data-local-id="a88ee0b3e468">Deep experience with search, retrieval, ranking or building RAG-based assistants</p> </li> <li> <p data-renderer-start-pos="3539" data-local-id="9b58081ace33">Strong understanding of modern deep learning, especially transformers and embeddings</p> </li> <li> <p data-renderer-start-pos="3627" data-local-id="3af7b74609d8">Experience with LLM-integrated or knowledge-intensive systems</p> </li> <li> <p data-renderer-start-pos="3692" data-local-id="f5f3ac6c678b">Experience designing evaluation frameworks and metrics for ML systems</p> </li> <li> <p data-renderer-start-pos="3765" data-local-id="e298f34817b3">Strong programming skills in Python</p> </li> <li> <p data-renderer-start-pos="3804" data-local-id="f3f98b81e4cd">Top-tier publications (<span data-highlighted="true" data-vc="highlighted-text"><span class="_1mT5xdRAKS"><span class="_0nmozVaHVx _2V7sgO2M4S _3BoeIDwZ7G _30zrXRyxdf _0ReiIH7zJH" data-testid="definition-highlighter">ICLR</span></span></span>, <span data-highlighted="true" data-vc="highlighted-text"><span class="_1mT5xdRAKS"><span class="_0nmozVaHVx _2V7sgO2M4S _3BoeIDwZ7G _30zrXRyxdf _0ReiIH7zJH" data-testid="definition-highlighter">ICML</span></span></span>, NeurIPS, <span data-highlighted="true" data-vc="highlighted-text"><span class="_1mT5xdRAKS"><span class="_0nmozVaHVx _2V7sgO2M4S _3BoeIDwZ7G _30zrXRyxdf _0ReiIH7zJH" data-testid="definition-highlighter">AAAI</span></span></span>, <span data-highlighted="true" data-vc="highlighted-text"><span class="_1mT5xdRAKS"><span class="_0nmozVaHVx _2V7sgO2M4S _3BoeIDwZ7G _30zrXRyxdf _0ReiIH7zJH" data-testid="definition-highlighter">EMNLP</span></span></span>, <span data-highlighted="true" data-vc="highlighted-text"><span class="_1mT5xdRAKS"><span class="_0nmozVaHVx _2V7sgO2M4S _3BoeIDwZ7G _30zrXRyxdf _0ReiIH7zJH" data-testid="definition-highlighter">ACL</span></span></span>)</p> </li> <li> <p data-renderer-start-pos="3869" data-local-id="f4b4b274060d">Ability to operate in a fast-moving, product-driven environment with high ownership and autonomy</p> </li> </ul> <p data-renderer-start-pos="3969" data-local-id="6863daca2e3d"><strong data-renderer-mark="true">Nice to haves</strong></p> <ul class="ak-ul" data-local-id="1277d9a5-56c4-4baf-b433-51bc8e50a5e5" data-indent-level="1"> <li> <p data-renderer-start-pos="3986" data-local-id="6710586b568c">Background in agentic AI systems (agents, tool use, autonomous workflows)</p> </li> <li> <p data-renderer-start-pos="4063" data-local-id="c8279fe831c2">Experience with <span data-highlighted="true" data-vc="highlighted-text"><span class="_1mT5xdRAKS"><span class="_0nmozVaHVx _2V7sgO2M4S _3BoeIDwZ7G _30zrXRyxdf _0ReiIH7zJH" data-testid="definition-highlighter">RL</span></span></span> post-training of LLMs or VLMs</p> </li> </ul> <p> </p> Find Jobs in Switzerland on Arbeitnow

Application Strategy

Targeted advice for this specific role

Apply in English

This role is listed in English — submit your CV and cover letter in English. Keep your CV to 1–2 pages and lead with measurable impact.

Clarify location requirements for the visa

This role is listed as hybrid. Note: even for remote roles, you typically need to physically reside in Germany (and be registered) to hold a German work visa. Confirm city requirements with HR.

Chancenkarte (Opportunity Card) alternative

If this company does not sponsor visas, the Chancenkarte lets you enter Germany for up to 1 year to find a job — no offer needed. You need a degree, 3 years of experience, and B1 German or C1 English, plus enough points on the scoring system.

Check Chancenkarte eligibility ↗

Opens the original job listing

Not sure if you qualify for a Blue Card?

Check your eligibility in 60 seconds →

Personalised guidance

CV feedback, interview prep, visa walkthrough, and moving advice — from someone who has actually done it.

12 years in German tech. Former hiring manager. Helped 15+ Indian professionals navigate the move — from application to Anmeldung.

Get personalised advice →
📄

Applying to Tavily? Your CV needs to match their standards.

Get a Germany-ready CV in 48 hours. Expert review with 12 years of German hiring experience.

Found a job worth applying for?

Learn how Indian professionals write the German CV, handle interviews, and negotiate salary — with 12 years of insider experience.

Germany Career Blueprint →

Planning your move to Germany?

Get weekly Blue Card IT jobs matched to your skills · Unsubscribe anytime

Need personalised guidance for your Germany move?

CV · interviews · visa · relocation · settling in — advice from someone who has done it. 12 years in German tech.

Get personalised advice →