{"id":779837,"url":"https://alion.io/job/stratum-machine-learning-ops-engineer","title":"Machine Learning Ops Engineer","company":{"id":720799,"name":"Stratum","domain":"stratum.gs","url":"https://alion.io/company/stratum-5","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","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":"2026-10-31T05:58:55Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":[],"countries":[],"hiring_countries":["CA"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":66000,"max_usd":144000,"period":"year","method":"role_seniority_country_cell","sample_n":29},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Computer Vision","optional":false},{"name":"Docker","optional":false},{"name":"Kubernetes","optional":false},{"name":"Machine Learning","optional":false},{"name":"NLP","optional":false},{"name":"NumPy","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Recommender Systems","optional":false},{"name":"SQL","optional":false},{"name":"DVC","optional":true},{"name":"Git","optional":true},{"name":"Kubeflow","optional":true},{"name":"MLFlow","optional":true},{"name":"OpenAI","optional":true},{"name":"Seldon Core","optional":true},{"name":"Spark","optional":true},{"name":"Weights & Biases","optional":true}],"status":"live","first_seen_at":"2025-05-31T22:21:33Z","employer_posted_date":"2025-05-31","last_verified_at":"2026-11-01T01:45:50Z","board_verified":true,"closed_at":null,"days_open":518,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":517},"description":"We are looking for a high-agency Machine Learning Ops Engineer to join our Infrastructure Team. You will help build and maintain the platform used to train, evaluate, and serve our AI models to clients in the mining industry. Your work will directly support our Technical Services and Platform teams in delivering solutions that create value for mining clients.\nThis position requires strong expertise in Python and machine learning workflows. You will work alongside a team of three engineers focused on creating robust infrastructure and tooling.\nThis is a remote-first position based in Canada.\nKey Responsibilities\nDevelop robust and well-tested code for core internal tools:\nCreate data preprocessing modules for mining data\n\nImplement metrics calculations and evaluation pipelines\n\nBuild visualization tools for 3D models and ML performance metrics\n\nTroubleshoot and fix issues in existing metrics code\n\nBuild and maintain our custom end-to-end MLOps platform:\nImplement experiment tracking systems\n\nCreate model registry with versioning and storage\n\nDevelop automated testing frameworks\n\nBuild interfaces between different components of the ML pipeline\n\nDevelop production-grade QA/QC systems for deployed AI models:\nImplement input data validation\n\nCreate automated alerts for performance issues\n\nSet up monitoring for data drift\n\nBuild dashboards for model performance metrics\n\nCreate specialized tools for mining data:\nImplement spatial data processing utilities\n\nBuild visualization tools for 3D geological data\n\nDevelop data converters between different mining data formats\n\nCreate utilities for coordinate transformations\n\nRefactor and productionize code created by the client services team:\nConvert notebooks into modular Python packages\n\nImplement proper error handling and logging\n\nAdd comprehensive testing to existing code\n\nImprove performance of data processing pipelines\n\nProvide technical expertise to the client services team\n\nManage infrastructure for data processing, model training, and serving\n\nMentor junior engineers, perform code reviews, and write documentation Proactively identify technical challenges and drive improvement initiatives\n\nTechnical Competencies & Requirements\nBachelor's degree in Computer Science, Engineering, or related fields OR equivalent experience in software development and ML engineering\n\n3+ years of industry experience Kubernetes, PyTorch\n\nAdvanced Python programming skills:\nProficiency with data science libraries (numpy, pandas)\n\nExperience with visualization tools\n\nAbility to write modular, robust, and tested Python code\n\nStrong debugging skills for complex ML systems\n\nDeep learning experience:\nImplementation of neural network models and training workflows\n\nUnderstanding of model architecture selection\n\nKnowledge of model evaluation techniques\n\nMLOps expertise:\nCreating experiment tracking systems\n\nBuilding model registries and versioning systems\n\nImplementing model deployment pipelines\n\nSetting up monitoring for model performance\n\nData engineering capabilities:\nExperience with SQL and database principles\n\nFamiliarity with database frameworks\n\nAbility to create data processing pipelines\n\nExperience handling common mining data formats and transformations\n\nInfrastructure management:\nExperience with cloud services (AWS/Azure)\n\nUnderstanding of containerization (Docker or Singularity)\n\nKnowledge of compute resources for ML\n\nTesting and quality assurance:\nImplementing automated tests for ML systems\n\nCreating QA/QC systems for model predictions\n\nDesigning validation steps for data inputs/outputs\n\nAbility to write efficient software following best practices\n\nProven ability to thrive in startup environments with low structure and high autonomy\n\nStrong technical communication skills and ability to collaborate in a remote team setting\n\nExperience working with machine learning in computer vision, NLP, recommender systems, or scientific applications\n\nStrong background in probability, machine learning, and data science\n\nStrong experience with data analysis/processing libraries such as pandas and numpy\n\nExcellent communication skills for both technical and non-technical audiences\n\nSelf-learner and motivated to pick up new skills\n\nNice to Have\nPrevious experience working at startups\n\nFamiliarity with Git, experiment tracking tools (WandB, Comet, etc.)\n\nExperience working on production machine learning using tools such as KubeFlow, MLFlow, AirFlow, Seldon Core, DVC, Spark, etc.\n\nWritten/oral fluency in a language besides English\n\nExperience optimizing data processing pipelines and/or neural network models\n\nProficiency in a lower-level programming language or GPU programming\n\nExperience with data application frameworks\n\nFull stack development experience\n\nExperience with experiment tracking systems and ML model monitoring\n\nBackground in mining or resource modeling\n\nAbout Stratum\nWe're Stratum, a mining software company with machine learning models as our core product. Our 3D maps predict how gold, silver, copper, etc. are distributed (and how much!) using only small amounts of data, unconventional data processing, and proprietary ML protocols. Our work directly affects how much money a mine is going to make next week/month/year while reducing waste/cost. We're supported by Founders Fund, Aramco, Builders VC, Y Combinator, and Ilya Sutskever, former Chief Scientist at OpenAI, who have recognized the potential of our industry-disrupting technology.\nOur long-term vision is to build a massive AI engine capable of making every decision in a mining operation, down to moving individual rocks. If you’re an exceptional engineer interested to helping make this vision a reality we look forward to reviewing your application and working together.","description_format":"text","description_chars":5742,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[{"language":"English","level":"All levels","optional":true}]},"benefits":[],"hiring_locations":[{"name":"Canada","iso":"CA","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Industrial AI"],"lifecycle":[{"event":"open","at":"2026-09-12T00:26:32Z"}],"visa":[],"liveness":{"score":3,"band":"cold","label":"Long shot","p_open":1,"p_active":0.123,"p_room":0.28,"age_days":517,"expected_fill_days":7,"reasons":["conf:1","stale_co","ghost","win:tail","crowd:"],"computed_at":"2026-10-31T05:58:55Z"},"pay":null,"html_url":"https://alion.io/job/stratum-machine-learning-ops-engineer","json_url":"https://alion.io/job/stratum-machine-learning-ops-engineer.json","meta":{"generated_at":"2026-11-01T03:02:19Z","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":4653,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-02T00:00:00Z"}},"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":720799},"rest":"https://alion.io/mcp/rest/get_company?id=720799"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fstratum-machine-learning-ops-engineer"},{"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%2Fstratum-machine-learning-ops-engineer"},{"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%2Fstratum-machine-learning-ops-engineer"},{"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/stratum-machine-learning-ops-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fstratum-machine-learning-ops-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":779837}},{"tool":"search_jobs","arguments":{"company":"stratum.gs","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":779837},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}