{"id":1141305,"url":"https://alion.io/job/avra-member-of-technical-staff-ml-systems-2","title":"Member of Technical Staff - ML Systems","company":{"id":2667009,"name":"avra","domain":"avracap.com","url":"https://alion.io/company/avra-2","size_band":null,"is_staffing_agency":false,"is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["Brazil"],"countries":["BR"],"hiring_countries":["BR"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":78000,"max_usd":175000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":775},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Ray","optional":false},{"name":"SkyPilot","optional":true}],"status":"live","first_seen_at":"2026-09-23T12:10:51Z","employer_posted_date":null,"last_verified_at":"2026-09-23T12:10:51Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"Job Description:\n Build CUDA kernels and compute primitives for training and serving graph neural networks (GNNs)\n Evolve Monad, the sampler and distributed-training library, including neighbor sampling and training performance\n Specify binary data formats (Lance, Arrow, CSR/CSC), and own materializations and feature backfills for training and evaluation\n Define data contracts and consumption requirements with teams building customer and proprietary datasets\n Build and operate experiment tracking, checkpoints, and evaluation infrastructure with reproducibility by default\n Own the model registry, lineage, versioning, and compatibility across models, embeddings, and downstream models\n Define and run release gates for governed production, batch, and on-premise model releases\n Enable auditing of the data, code, configuration, and evidence that produced each release\n Improve time-to-experiment, time-to-governed-release, GPU training throughput, release records, lineage, and reproducibility\nRequirements:\n Strong systems engineering skills and production-quality Python\n Experience with distributed training (e.g., Ray, PyTorch distributed) and multi-node GPU workloads\n Experience with columnar data formats and large-scale data materialization\n Familiarity with ML lifecycle tooling: experiment tracking, model registries, evaluation, and reproducibility\n A product mindset: treat an internal platform as a product with real users\n CUDA kernel development or GPU performance optimization (nice to have)\n Graph neural networks or graph sampling at scale (nice to have)\n Lance, Arrow, or other columnar/indexed storage formats (nice to have)\n Multi-cloud GPU compute (e.g., SkyPilot) (nice to have)\n Model governance or audit requirements in financial services or other regulated environments (nice to have)\nBenefits:","description_format":"text","description_chars":1826,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Brazil","iso":"BR","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence"],"lifecycle":[{"event":"open","at":"2026-09-23T12:10:51Z"}],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":18,"reasons":["seen:0","win:early"],"computed_at":"2026-09-24T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/avra-member-of-technical-staff-ml-systems-2","json_url":"https://alion.io/job/avra-member-of-technical-staff-ml-systems-2.json","meta":{"generated_at":"2026-09-25T04:28:18Z","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":4847,"day_limit":5000,"remaining_today":153,"minute_limit":60,"resets_at":"2026-09-26T00:00:00Z"}}}