{"id":1222511,"url":"https://alion.io/job/dunia-materials-informatics-scientist-evaluation-focused","title":"Materials Informatics Scientist (Evaluation-focused)","company":{"id":2222519,"name":"Dunia","domain":"dunia.ai","url":"https://alion.io/company/dunia-ai","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Personio","truth_index":{"grade":"D","score":40,"open_postings":11,"ghost_share":1,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-03T05:45:00Z"}},"role":"Science & Research","role_family":"Science & Research","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Berlin, Germany"],"countries":["DE"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":69000,"max_usd":145000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":837},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Machine Learning","optional":false},{"name":"Python","optional":false}],"status":"live","first_seen_at":"2026-02-02T18:05:36Z","employer_posted_date":"2026-02-02","last_verified_at":"2026-10-03T05:43:23Z","board_verified":true,"closed_at":null,"days_open":243,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":242},"description":"Your mission\n Define how AI models for materials discovery are evaluated, compared, and trustedDunia is building AI for one of the hardest unsolved problems in science: turning materials discovery from an academic, trial-and-error process into a programmable, scalable discipline.\nAs our models grow more complex and our experimental throughput increases, the limiting factor is no longer generating predictions, but knowing which ones to believe.\nAs Materials Informatics Scientist (Evaluation-focused), you will own the evaluation and validation of AI models applied to materials discovery. Your role is to ensure that model performance claims are meaningful, comparable, and decision-relevant, and that progress in AI for Materials reflects real improvements in discovery, not artifacts of metrics or datasets.\nThis role is not about building new models. It is about defining the standards by which models are judged.\n\nYour tasks will include:\nOwn evaluation as a scientific discipline\nDesign, implement, and maintain evaluation frameworks for AI models across materials discovery tasks\nDefine metrics and protocols that reflect generalization, robustness, uncertainty, and experimental relevance\nIdentify failure modes, dataset leakage, and misleading performance signals\nInterrogate and compare models\nSystematically benchmark different model classes, training regimes, and representations\nEvaluate tradeoffs between accuracy, uncertainty, data efficiency, and usability\nProvide clear, defensible recommendations on which models to trust, deploy, or retire\nConnect AI performance to real outcomes\nLink model behavior to experimental results and program-level objectives\nDistinguish improvements that change decisions from those that only improve abstract scores\nHelp research and programs teams understand what current models can and cannot reliably do\nBuild robust analytical tooling\nDevelop and maintain professional-grade scripts and analysis pipelines for evaluation and benchmarking\nVisualize complex, high-dimensional results in ways that surface real insight\nEnsure disciplined, reproducible handling of data, code, and results\nCommunicate truth clearly\nPresent findings clearly to AI researchers, materials scientists, and leadership\nProduce concise summaries that align the organization around a shared view of evidence and uncertainty\nAct as an independent scientific reference point when claims require validation\nYour profile\nPhD (strongly preferred) or Master’sdegree in materials science, chemistry, physics, machine learning, or a related field\nSignificant experience (typically 5-8 years) working with scientific or ML systems under real-world uncertainty\nDemonstrated experience evaluating, benchmarking, orvalidatingmodels rather than only building them\nStrong programming skills in Python and scientific data tooling\nDeep appreciation for rigor, reproducibility, and careful interpretation of results\nEnglish fluency, additionallanguages preferred","description_format":"text","description_chars":2971,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":true},"security_clearance":false,"languages":[{"language":"English","level":"Advanced (C1)","optional":true}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-09-25T12:38:24Z"}],"visa":[],"liveness":{"score":5,"band":"cold","label":"Long shot","p_open":1,"p_active":0.167,"p_room":0.28,"age_days":242,"expected_fill_days":30,"reasons":["conf:0","stale_co","ghost","win:tail","crowd:"],"computed_at":"2026-10-03T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/dunia-materials-informatics-scientist-evaluation-focused","json_url":"https://alion.io/job/dunia-materials-informatics-scientist-evaluation-focused.json","meta":{"generated_at":"2026-10-04T00:30:05Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":614,"day_limit":5000,"remaining_today":4386,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}