{"id":1456343,"url":"https://alion.io/job/humyn-labs-data-engineer","title":"Data Engineer","company":{"id":47368,"name":"Humyn Labs","domain":"humynlabs.ai","url":"https://alion.io/company/humyn-labs","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"middle","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":16000,"max_usd":39000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":13},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"Amazon S3","optional":false},{"name":"Apache Hudi","optional":false},{"name":"AWS","optional":false},{"name":"Delta Lake","optional":false},{"name":"DynamoDB","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":false},{"name":"Hugging Face","optional":true},{"name":"Ray","optional":true},{"name":"SLURM","optional":true}],"status":"live","first_seen_at":"2026-09-29T09:58:49Z","employer_posted_date":null,"last_verified_at":"2026-09-29T09:58:49Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"Requirements:\n4+ years in a data engineering role with end-to-end pipeline ownership.\nStrong Python async patterns, subprocess management, API clients, and data processing at scale.\nHands-on AWS Athena, Glue, S3, DynamoDB, and Lake Formation; production-grade, not just familiarity.\nApache Hudi or Delta Lake schema evolution, partition strategies, and upsert patterns.\nSQL proficiency: able to write and optimize complex analytical queries.\nExperience with Airflow or an equivalent workflow orchestrator.\nDemonstrated experience with large-scale media data pipelines, audio/video format conversion, metadata extraction, and chunking, e. g., egocentric or multimodal datasets (hard requirement, not a plus).\nUnderstanding of how data format and I/O design affect downstream GPU compute workloads (WebDataset, sharded Parquet, tfrecord, or equivalent).\nNice to Have:\nDirect experience designing data handoff for GPU clusters (AWS Batch GPU instances, Ray, or SLURM).\nFamiliarity with ML training data formats and dataset standards used by AI labs (Hugging Face datasets, WebDataset, dataset cards).\nExperience with rclone, large-scale file transfer, or cloud-to-cloud sync pipelines.\nExposure to data lineage or provenance tooling (OpenLineage, DataHub, or custom metadata schemas).","description_format":"text","description_chars":1281,"description_truncated":false,"requirements":{"experience_years_min":4,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","AI Training Data & Annotation"],"lifecycle":[{"event":"open","at":"2026-09-29T09:58:49Z"}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":1,"expected_fill_days":18,"reasons":["seen:1","velocity","win:early"],"computed_at":"2026-10-01T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/humyn-labs-data-engineer","json_url":"https://alion.io/job/humyn-labs-data-engineer.json","meta":{"generated_at":"2026-10-01T09:40:26Z","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":374,"day_limit":5000,"remaining_today":4626,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}