{"id":2938820,"url":"https://alion.io/job/thepsi-data-and-ai-architect","title":"Data and AI Architect","company":{"id":44642,"name":"Thepsi","domain":"thepsi.com","url":"https://alion.io/company/thepsi","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Jaipur, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":27000,"max_usd":63000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":13},"experience_years_min":8,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon Redshift","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Dagster","optional":false},{"name":"Dask","optional":false},{"name":"Dimensional Modeling","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Google BigQuery","optional":false},{"name":"Google Cloud Spanner","optional":false},{"name":"LLM","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Prefect","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false}],"status":"live","first_seen_at":"2026-10-20T16:35:00Z","employer_posted_date":null,"last_verified_at":"2026-10-20T16:35:00Z","board_verified":false,"closed_at":null,"days_open":6,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":6},"description":"We are looking for a Lead Data Architect to design, build, and scale our data pipelines and entity resolution systems. This role combines deep technical expertise in data engineering with hands-on experience in AI-assisted tooling, entity matching, and data integration from diverse sources. You will lead architectural decisions for our data platform, mentor engineers, and ensure our pipelines are reliable, scalable, and production-grade.\n\nResponsibilities: \nArchitect, build, and maintain robust, scalable data pipelines that ingest, transform, and serve data from multiple internal and external sources.\nOwn the end-to-end orchestration of data workflows using tools like Dagster, ensuring observability, reliability, and maintainability of pipelines.\nDesign and implement entity resolution workflows including matching, merging, and survivorship logic using tools such as Splink to produce clean, deduplicated, golden records.\nBuild and maintain web scrapers to source data from external providers, ensuring resilience to source changes, rate limits, and data quality issues.\nIntegrate and reconcile data coming from multiple, often inconsistent, sources into unified, trustworthy datasets.\nDesign and maintain data models and schemas across transactional and analytical systems, ensuring consistency, scalability, and performance.\nLeverage AI/LLM-based tools and techniques to enhance data pipeline capabilities, e. g., intelligent data extraction, automated data quality checks, or AI-assisted entity matching.\nDefine and enforce best practices around pipeline design, testing, monitoring, and documentation.\nCollaborate closely with data engineers, product managers, and other stakeholders to translate business requirements into scalable data architecture.\nProvide technical leadership and mentorship to the data engineering team.\n\nRequirements: \nStrong hands-on experience building and maintaining production-grade data pipelines at scale.\nPractical experience with Dagster (or similar orchestration tools like Airflow/Prefect) for pipeline orchestration.\nExperience with Splink or similar probabilistic/deterministic record linkage tools for entity matching, merging, and survivorship.\nStrong proficiency in Python, including experience writing and maintaining web scrapers.\nProven experience integrating and maintaining data pipelines that pull from multiple, heterogeneous data sources.\nExperience applying AI/ML tools within data engineering workflows (e. g., LLM-assisted data cleaning, extraction, or matching).\nHands-on experience with relational and distributed databases such as PostgreSQL and Google Cloud Spanner.\nStrong understanding of data modelling principles (normalisation, dimensional modelling, schema design) across OLTP and OLAP systems.\nExperience with cloud data warehousing platforms such as BigQuery, Redshift, and cloud platforms (GCP/AWS/Azure).\nStrong communication skills and experience working cross-functionally with engineering and product teams.\nExperience with distributed data processing frameworks (e. g., Spark, Dask).\nFamiliarity with data governance, lineage, and cataloguing tools.\nPrior experience in a lead or architect-level role guiding a data engineering team.\nSkills\nAirflow, Dagster, ETL, Prefect, Spark, Splink, data, orchestration, pipeline, pipelines, python","description_format":"text","description_chars":3319,"description_truncated":false,"requirements":{"experience_years_min":8,"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","IT Outsourcing & Dedicated Teams","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-20T16:35:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":5,"expected_fill_days":30,"reasons":["seen:5","velocity","win:early"],"computed_at":"2026-10-26T05:57:25Z"},"pay":null,"html_url":"https://alion.io/job/thepsi-data-and-ai-architect","json_url":"https://alion.io/job/thepsi-data-and-ai-architect.json","meta":{"generated_at":"2026-10-26T21:44:07Z","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":"search","counted_by":"address","units_charged":0,"used_today":0,"day_limit":null,"remaining_today":null,"minute_limit":null,"resets_at":"2026-10-27T00:00:00Z"}},"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":44642},"rest":"https://alion.io/mcp/rest/get_company?id=44642"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fthepsi-data-and-ai-architect"},{"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%2Fthepsi-data-and-ai-architect"},{"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%2Fthepsi-data-and-ai-architect"},{"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/thepsi-data-and-ai-architect\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fthepsi-data-and-ai-architect"}]}