{"id":2705848,"url":"https://alion.io/job/cloudesign-data-engineer","title":"Data Engineer","company":{"id":2994,"name":"Cloudesign","domain":"cloudesign.com","url":"https://alion.io/company/cloudesign","size_band":"11-50","is_staffing_agency":false,"employer_type":"services","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":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":14000,"max_usd":34000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":16},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"Apache Kafka","optional":false},{"name":"BigQuery","optional":false},{"name":"CockroachDB","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Google BigQuery","optional":false},{"name":"PostgreSQL","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":false},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-10-16T11:07:00Z","employer_posted_date":null,"last_verified_at":"2026-10-16T11:07:00Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"About the Role : \n\nWe are looking for a hands-on Data Engineer to design, build, and maintain robust streaming ETL pipelines.\n\nUsing Python, Confluent, and Google Cloud Platform (GCP), you will work with event-driven architecture to develop production-quality data systems.\n\nYou will help ensure the reliability and performance of existing data systems, components, and platforms.\n\nWorking closely with technology teams, you will support the seamless collection and transfer of critical data.\n\nThis role requires strong software engineering fundamentals, clean and efficient coding practices, and the ability to deliver practical solutions to business challenges.\n\nYou will also contribute to technical solution design, team support, and engineering best practices.\n\nEssential Skills : \n\n- Strong programming skills, particularly in Python.\n\n- Significant experience with relational or NoSQL databases, such as SQL Server, CockroachDB, or PostgreSQL.\n\n- Proven experience designing and building efficient, scalable data pipelines.\n\n- Experience scheduling and maintaining automated workflows, particularly with Apache Airflow.\n\n- Ability to write clean, understandable, maintainable code and documentation.\n\n- Experience building streaming pipelines using Kafka and/or the Confluent platform.\n\n- Experience developing streaming pipelines on GCP, using services such as Pub/Sub, BigQuery, Google Cloud Storage (GCS), and Dataflow.\n\n- Strong understanding of ETL pipelines and the ability to build pipelines from scratch.\n\n- Strong communication, collaboration, and teamwork skills.\n\nKey Responsibilities : \n\n- Independently plan, design, and deliver high-quality, production-ready data solutions that are scalable, globally distributed, and highly available.\n\n- Develop systems using event-driven architecture, with a focus on performance, resilience, and fault tolerance.\n\n- Write clean, reliable, and maintainable code, favouring simplicity and selecting the right tools for the task.\n\n- Collaborate with cross-functional teams to build and optimise business-critical data pipelines.\n\n- Communicate effectively with technical and non-technical stakeholders to align on objectives and share progress.\n\n- Participate in code reviews, pair programming, and knowledge-sharing activities to strengthen team capabilities and maintain engineering standards.\n\n- Support project delivery through practical estimation, progress tracking, and technical support for system and user issues.\n\n- Adapt to new technologies and challenges while promoting continuous improvement and shared ownership.\n\nEqual Opportunity : \n\nWe are committed to creating an inclusive, respectful, and merit-based workplace.\n\nEmployment decisions are made without discrimination on any basis protected by applicable law.\n\nApplications from candidates of all backgrounds are encouraged, and reasonable accommodation can be provided throughout the recruitment process where required.\n\nRequired Skills : \n\n- Pyspark\n\n- Python\n\n- GCP\n\n- Data Engineer\n\n- ETL\n\n- Orchestration\nSkills\nPython, ETL, PySpark, Apache Airflow, Kafka, BigQuery, SQL Server, PostgreSQL, Data Engineering, Google Cloud Platform, Data Pipeline","description_format":"text","description_chars":3175,"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":["IT Consulting & Digital Transformation","Software Testing & QA","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-16T12:29:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":0,"expected_fill_days":30,"reasons":["seen:0","velocity","win:early"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/cloudesign-data-engineer","json_url":"https://alion.io/job/cloudesign-data-engineer.json","meta":{"generated_at":"2026-10-17T12:43:53Z","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":16933,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"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":2994},"rest":"https://alion.io/mcp/rest/get_company?id=2994"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcloudesign-data-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%2Fcloudesign-data-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%2Fcloudesign-data-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/cloudesign-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcloudesign-data-engineer"}]}