{"id":1141306,"url":"https://alion.io/job/avra-member-of-technical-staff-inference-platform-2","title":"Member of Technical Staff - Inference Platform","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,"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","hiring_geo_confidence":"inferred","locations":["Brazil"],"countries":["BR"],"hiring_countries":["BR"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":80000,"max_usd":179000,"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":"Fine-tuning","optional":false},{"name":"Kubernetes","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"Sophos","optional":false},{"name":"Amazon EKS","optional":true},{"name":"AWS","optional":true},{"name":"GCP","optional":true},{"name":"Google GKE","optional":true},{"name":"Ray","optional":true},{"name":"Ray Serve","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":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"Job Description:\n Own execution environments for models on the Platform team\n Evolve Sophos, the online and batch inference runtime built on Kubernetes\n Run large batch inference on ephemeral jobs using multi-dimensional admission control through Kueue\n Build and extend the Sophos controller and Kubernetes custom resources\n Optimize model inference engines and feature processing using vectorized, columnar operations\n Serve graphs and data efficiently from Lance-based storage\n Own training, post-training, and fine-tuning jobs in Avra's cloud and customer dataplanes\n Drive autoscaling, GPU serving, performance, and cost optimization with telemetry for every model\n Solve deterministic job sizing, checkpointing and recovery, customer encryption and isolation, input-file resilience, and automatic profiling\n Achieve 99.9% serving availability, low online-inference latency, high batch throughput, optimized costs, GPU utilization, and reliable job completion\nRequirements:\n Experience running model serving or large-scale batch compute on Kubernetes\n Experience building Kubernetes controllers or operators\n Skill at profiling and optimizing data-heavy Python pipelines\n Clear sense of cost and compute efficiency\n Production-quality code and code review experience\n Willingness to operate what you build\n Nice-to-have: Ray, Ray Serve, or KubeRay in production\n Nice-to-have: Kueue or other batch scheduling and admission-control systems\n Nice-to-have: GPU serving and performance optimization\n Nice-to-have: Arrow, Parquet, Lance, or other columnar formats\n Nice-to-have: Shipping software to customer-hosted Kubernetes\n Nice-to-have: GCP/AWS, GKE/EKS, and experience in financial services or regulated environments\nBenefits:","description_format":"text","description_chars":1732,"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":[],"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-inference-platform-2","json_url":"https://alion.io/job/avra-member-of-technical-staff-inference-platform-2.json","meta":{"generated_at":"2026-09-24T08:49:16Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers"}}