{"id":1576896,"url":"https://alion.io/job/cleardemand-machine-learning-engineer-de","title":"Machine Learning Engineer (DE)","company":{"id":3847847,"name":"Cleardemand","domain":"cleardemand.com","url":"https://alion.io/company/cleardemand","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"BambooHR","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"Amazon Redshift","optional":false},{"name":"Apache Hudi","optional":false},{"name":"AWS","optional":false},{"name":"AWS Glue","optional":false},{"name":"BigQuery","optional":false},{"name":"Databricks","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Google BigQuery","optional":false},{"name":"Python","optional":false},{"name":"Snowflake","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Embeddings","optional":true}],"status":"live","first_seen_at":"2026-06-02T00:00:00Z","employer_posted_date":"2026-06-02","last_verified_at":"2026-10-16T19:43:43Z","board_verified":true,"closed_at":null,"days_open":136,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":136},"description":"The role requires someone who can bridge data engineering and ML engineering by ensuring that high-quality, well-structured, scalable data flows are available for model training, inference, evaluation, and business reporting.\nKey Responsibilities\nBuild, maintain, and optimize data pipelines that support ML/ Model workflows, Decision systems, model inference, and validation processes.\nWork with large-scale structured and semi-structured datasets across product catalogs, competitor data, customer data, match data, and validation data.\nDevelop robust ETL / ELT workflows using Python, SQL, Spark or equivalent distributed processing frameworks.\nSupport feature generation, data reconciliation, data quality checks, and data observability for ML systems.\nCollaborate with ML Engineers and Data Scientists to prepare clean, reliable datasets for model training, evaluation, and inference.\nImprove pipeline performance, scalability, reliability, and cost efficiency.\nBuild reusable data processing components and automation utilities.\nDebug data discrepancies across upstream and downstream systems.\nSupport operational reporting, dashboards, metric pipelines, and audit workflows.\nWork closely with engineering teams to productionize ML data flows and ensure smooth handoffs between data systems and ML systems.\nRequired Skills\nStrong programming skills.\nHands-on experience with data processing pipelines and large datasets.\nGood understanding of ETL / ELT design, data modeling, partitioning, incremental processing, and data validation.\nExperience with tools or platforms such as Spark, Airflow, AWS Glue, Apache Hudi, Databricks, BigQuery, Snowflake, Redshift, Athena, or similar technologies.\nAbility to debug data quality issues and trace data across systems.\nExperience building monitoring, reconciliation, or data quality frameworks.\nGood understanding of APIs, file formats, and data storage formats \nStrong with cloud platforms, preferably AWS and GCP.\nBasic understanding of ML workflows such as training data preparation, inference data generation, evaluation datasets, and feature engineering.\nExperience working with ML pipelines or MLOps workflows.\nAbility to write clean, modular, maintainable, and well-documented code.\nGood to Have\nExposure to vector databases, embeddings, search systems, or retrieval-based systems.\nExperience with product catalog data, e-commerce data, taxonomy, attributes, or entity matching.\nUnderstanding of model evaluation datasets and metric generation.","description_format":"text","description_chars":2499,"description_truncated":false,"requirements":{"experience_years_min":null,"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":["Cybersecurity","Brewing & Beer","Retail & Pricing Analytics"],"lifecycle":[{"event":"open","at":"2026-10-01T10:35:57Z"}],"visa":[],"liveness":{"score":6,"band":"cold","label":"Long shot","p_open":1,"p_active":0.21,"p_room":0.28,"age_days":136,"expected_fill_days":33,"reasons":["conf:3","win:tail","crowd:"],"computed_at":"2026-10-16T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/cleardemand-machine-learning-engineer-de","json_url":"https://alion.io/job/cleardemand-machine-learning-engineer-de.json","meta":{"generated_at":"2026-10-16T19:48:53Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":191,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-17T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":3847847},"rest":"https://alion.io/mcp/rest/get_company?id=3847847"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcleardemand-machine-learning-engineer-de"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fcleardemand-machine-learning-engineer-de"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fcleardemand-machine-learning-engineer-de"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/cleardemand-machine-learning-engineer-de\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcleardemand-machine-learning-engineer-de"}]}