{"id":964624,"url":"https://alion.io/job/citi-data-engineer-python-ai","title":"Data Engineer - Python, AI","company":{"id":7841,"name":"Citi","domain":"citi.com","url":"https://alion.io/company/citi","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"A","score":99,"open_postings":541,"ghost_share":0.006,"stale_share":0.168,"repost_share":0.068,"time_to_fill_p50_days":9,"computed_at":"2026-11-04T06:34:25Z"}},"role":"Data Science","role_family":"Data Science","seniority":"middle","employment_type":"full_time","work_mode":"hybrid","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":13000,"max_usd":34000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":21},"experience_years_min":10,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon ECS","optional":false},{"name":"BERT","optional":false},{"name":"Boto3","optional":false},{"name":"CI/CD","optional":false},{"name":"ETL/ELT","optional":false},{"name":"FastAPI","optional":false},{"name":"Flask","optional":false},{"name":"GitHub","optional":false},{"name":"Hugging Face","optional":false},{"name":"Linux","optional":false},{"name":"LLM","optional":false},{"name":"MLFlow","optional":false},{"name":"NLP","optional":false},{"name":"Pandas","optional":false},{"name":"pySpark","optional":false},{"name":"Pytest","optional":false},{"name":"Python","optional":false},{"name":"Redis","optional":false},{"name":"Rest API","optional":false},{"name":"Transformers","optional":false},{"name":"AWS","optional":true},{"name":"Dask","optional":true},{"name":"Docker","optional":true},{"name":"Git","optional":true},{"name":"Kubernetes","optional":true},{"name":"Polars","optional":true},{"name":"PyTorch","optional":true},{"name":"Spark","optional":true},{"name":"TensorFlow","optional":true}],"status":"live","first_seen_at":"2026-09-16T13:03:36Z","employer_posted_date":"2026-10-09","last_verified_at":"2026-11-04T05:08:58Z","board_verified":true,"closed_at":null,"days_open":48,"trust":{"level":"ok","repost_count":1,"flags":[],"days_open":48},"description":"Role Summary\nWe are looking for a mid-level Python Developer with combined experience in Data Engineering andAI/NLP engineering. The candidate will build NLP pipelines using libraries such as Flair, BERT, and LLM frameworks, and will also work on large-scale data processing using PySpark, Pandas, and related data tools. The role includes developing APIs, integrating with platform services, and supporting CI/CD deployments using GitHub and LightSpeed Enterprise.\nKey Responsibilities\nDevelop and optimize ETL/data processing jobs using PySpark, Pandas, PyArrow, and related libraries.\nBuild and maintain NLP pipelines using Flair, BERT, and LLM-based models.\nDevelop scalable ingestion and data transformation pipelines for AI and analytics use cases.\nBuild and maintain Flask-based APIs for model inference and service integrations.\nUse regular expressions for text cleaning, parsing, and NLP preprocessing.\nIntegrate caching and fast lookups using Redis.\nManage and deploy ML models using MLflow for tracking and versioning.\nSupport CI/CD workflows using GitHub, LightSpeed Enterprise, and deployment pipelines.\nCreate and maintain Autosys JILs for job scheduling and automation.\nUse basic Linux commands for troubleshooting, operations, and deployment tasks.\nMonitor application and system health using ITRS Geneos.\nWrite unit tests and improve automation test coverage (PyTest/unittest).\nWork with REST APIs, microservices, and basic shell scripting.\nWork with cloud services (ECS), including boto3.\nRequired Skills\n10-12 years of hands-on Python programming experience.\nStrong fundamentals in Python, OOP, and design patterns.\nExperience with NLP libraries such as Flair, BERT, HuggingFace Transformers, or similar.\nSolid experience with PySpark, Pandas, PyArrow, and distributed data pipelines.\nExperience building APIs using Flask (FastAPI is a plus).\nExperience with MLflow for model tracking and deployment.\nGood understanding of CI/CD practices and Git workflows.\nExperience working with Redis or similar in-memory stores.\nExperience with Autosys JILs for job scheduling.\nComfortable with Linux command line and shell scripting.\nStrong debugging, problem-solving, and teamwork skills.\nExposure to cloud services; AWS boto3 experience is an asset.\nNice-to-Have\nExperience with Polars or Dask for high-performance data processing.\nExperience with PyTorch or TensorFlow for model training.\nExperience with Docker, Kubernetes, or containerized deployments.\nExperience with monitoring tools such as ITRS Geneos.\nExperience with FastAPI, Airflow, or Prefect.\n------------------------------------------------------\nJob Family Group:\nTechnology------------------------------------------------------\nJob Family:\nApplications Development------------------------------------------------------\nTime Type:\nFull time------------------------------------------------------\nMost Relevant Skills\nPlease see the requirements listed above.------------------------------------------------------\nOther Relevant Skills\nFor complementary skills, please see above and/or contact the recruiter.------------------------------------------------------\nCiti is an equal opportunity employer, and qualified candidates will receive consideration without regard to their race, color, religion, sex, sexual orientation, gender identity, national origin, disability, status as a protected veteran, or any other characteristic protected by law.\nIf you are a person with a disability and need a reasonable accommodation to use our search tools and/or apply for a career opportunity review Accessibility at Citi.\nView Citi’s EEO Policy Statement and the Know Your Rights poster.","description_format":"text","description_chars":3653,"description_truncated":false,"requirements":{"experience_years_min":10,"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":["Artificial Intelligence","Financial Services","Payment Processing & Gateways","Consumer Loans & Pawnshops"],"lifecycle":[{"event":"open","at":"2026-09-16T13:03:36Z"},{"event":"close","at":"2026-09-24T18:36:23Z"},{"event":"reopen","at":"2026-10-10T12:39:15Z"}],"visa":[],"liveness":{"score":9,"band":"cold","label":"Long shot","p_open":1,"p_active":0.307,"p_room":0.28,"age_days":48,"expected_fill_days":9,"reasons":["conf:1","velocity","win:tail","crowd:brand"],"computed_at":"2026-11-04T06:34:25Z"},"pay":null,"html_url":"https://alion.io/job/citi-data-engineer-python-ai","json_url":"https://alion.io/job/citi-data-engineer-python-ai.json","meta":{"generated_at":"2026-11-04T07:19:33Z","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":11446,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-05T00:00:00Z"}},"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":7841},"rest":"https://alion.io/mcp/rest/get_company?id=7841"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fciti-data-engineer-python-ai"},{"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%2Fciti-data-engineer-python-ai"},{"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%2Fciti-data-engineer-python-ai"},{"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/citi-data-engineer-python-ai\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fciti-data-engineer-python-ai"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":964624}},{"tool":"search_jobs","arguments":{"company":"citi.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":964624},"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"}}