{"id":1292922,"url":"https://alion.io/job/avisoft-senior-real-time-data-engineer","title":"Senior Real-Time Data Engineer","company":{"id":3801200,"name":"Avisoft","domain":"avisoft.io","url":"https://alion.io/company/avisoft-2","size_band":null,"is_staffing_agency":false,"employer_type":"staffing","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["India"],"countries":["IN"],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":21000,"max_usd":43000,"period":"year","method":"role_seniority_country_cell","sample_n":57},"experience_years_min":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon Kinesis","optional":false},{"name":"Apache Kafka","optional":false},{"name":"ClickHouse","optional":false},{"name":"Flink","optional":false},{"name":"GraphQL","optional":false},{"name":"Node JS","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Python","optional":false},{"name":"Rest API","optional":false},{"name":"SQL","optional":false},{"name":"StarRocks","optional":false},{"name":"JavaScript","optional":true},{"name":"Kubernetes","optional":true},{"name":"Terraform","optional":true}],"status":"live","first_seen_at":"2026-08-11T03:57:52Z","employer_posted_date":null,"last_verified_at":"2026-08-11T03:57:52Z","board_verified":false,"closed_at":null,"days_open":48,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":48},"description":"Job Summary :\n\nWe are looking for a Senior Real-Time Data Engineer to lead the architecture and development of a high-performance, customer-facing analytics engine. The role focuses on processing millions of real-time events and transforming raw data into reliable, actionable insights.\n\nKey Responsibilities :\n\n- Design and maintain a low-latency analytics architecture capable of supporting high-concurrency queries.\n\n- Build and optimize real-time ingestion pipelines from PostgreSQL and event streams such as Kafka/Kinesis into Apache Pinot.\n\n- Develop semantic models using Cube.js to create consistent business metrics across dashboards, reports, and APIs.\n\n- Optimize Apache Pinot tables, indexing strategies, and Cube.js pre-aggregations for high-performance analytics.\n\n- Design and expose data models through REST/GraphQL APIs.\n\n- Collaborate with frontend engineers to support analytics and data visualization requirements.\n\n- Implement multi-tenant security and ensure strict data isolation between customer accounts.\n\n- Optimize analytical queries, data pipelines, and backend services for scalability and low latency.\n\n- Translate complex business requirements into scalable data models and semantic-layer implementations.\n\nMust-Have Skills :\n\n- 7 - 12 years of experience in Data Engineering / Analytics Engineering.\n\n- 3+ years of production experience with Apache Pinot or similar OLAP technologies such as ClickHouse/StarRocks.\n\n- Strong hands-on experience with Cube.js (Semantic modeling, Pre-aggregations, Security contexts, Multi-tenant configurations).\n\n- Expert-level PostgreSQL knowledge (Analytical query optimization, Complex SQL, Performance tuning, CDC).\n\n- Hands-on experience with real-time data ingestion and streaming technologies : Kafka, Kinesis, Debezium, Flink.\n\n- Strong proficiency in SQL and ability to translate business logic into data models.\n\n- Strong programming experience in Python or Node.js.\n\n- Experience developing scalable backend services and APIs.\n\nPreferred Skills :\n\n- Experience building analytics platforms for CRM, Sales Technology, or SaaS products.\n\n- Experience with Terraform and Kubernetes.\n\n- Experience managing and scaling data clusters.\n\n- Open-source contributions to Apache Pinot, Cube.js, or related projects.\n\n- Experience with REST and GraphQL APIs.\n\n- Strong understanding of distributed systems and real-time analytics architecture.\n\nSkills\nData Engineering, Data Pipeline, Data Ingestion, OLAP, ClickHouse, Kafka, Apache Flink, SQL, PostgreSQL","description_format":"text","description_chars":2519,"description_truncated":false,"requirements":{"experience_years_min":7,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Custom Software Development","AI Consulting & Integration"],"lifecycle":[{"event":"open","at":"2026-09-26T08:01:01Z"}],"liveness":{"score":9,"band":"cold","label":"Long shot","p_open":0.4,"p_active":0.484,"p_room":0.45,"age_days":48,"expected_fill_days":30,"reasons":["seen:48","velocity","win:tail"],"computed_at":"2026-09-28T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/avisoft-senior-real-time-data-engineer","json_url":"https://alion.io/job/avisoft-senior-real-time-data-engineer.json","meta":{"generated_at":"2026-09-29T03:06:11Z","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":2781,"day_limit":5000,"remaining_today":2219,"minute_limit":60,"resets_at":"2026-09-30T00:00:00Z"}}}