{"id":1621283,"url":"https://alion.io/job/exl-data-scientist-5","title":"Data Scientist","company":{"id":38016,"name":"EXL","domain":"exlservice.com","url":"https://alion.io/company/exl","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Oracle","truth_index":{"grade":"B","score":80,"open_postings":54,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":9,"computed_at":"2026-10-05T05:45:15Z"}},"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":14500,"max_usd":35000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":13},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Apache Kafka","optional":false},{"name":"Apache Pulsar","optional":false},{"name":"AutoGen","optional":false},{"name":"Embeddings","optional":false},{"name":"FastAPI","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"LangChain","optional":false},{"name":"Langfuse","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Pinecone","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Pydantic","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Rest API","optional":false},{"name":"SQL","optional":false},{"name":"WebSockets","optional":false},{"name":"Claude","optional":true},{"name":"Prompt Engineering","optional":true}],"status":"closed","first_seen_at":"2026-09-30T15:47:00Z","employer_posted_date":"2026-09-30","last_verified_at":"2026-10-03T01:09:12Z","board_verified":false,"closed_at":"2026-10-03T01:09:12Z","days_open":2,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":2},"description":"Key Responsibilities\nTechnical Execution\nBuild and maintain high-performance REST/WebSocket APIs using FastAPI (Pydantic v2)\nImplement and optimize agentic AI systems using frameworks like LangGraph, Deep Agents, AutoGen, and LangChain\nArchitect real-time, event-driven microservices using messaging queues like Apache Kafka\nDesign clean, testable, maintainable services using SOLID principles, Python async, and type hints\nIntegrate and optimize SQL, NoSQL, and vector databases (Postgres, MongoDB, ChromaDB, Pinecone)\nRun LangGraph/Deep Agents workflows in production with checkpointing, persistence, and human-in-the-loop controls, backed by LLM observability and evaluation tooling (e.g., LangSmith, Langfuse)\nApply LLM safety guardrails (prompt-injection mitigation, PII handling, content moderation) in line with Banking, Insurance, and Healthcare compliance requirements\nStay current with emerging trends in GenAI, deep learning, and AI orchestration frameworks\nKey Responsibilities\nTechnical Execution\nBuild and maintain high-performance REST/WebSocket APIs using FastAPI (Pydantic v2)\nImplement and optimize agentic AI systems using frameworks like LangGraph, Deep Agents, AutoGen, and LangChain\nArchitect real-time, event-driven microservices using messaging queues like Apache Kafka\nDesign clean, testable, maintainable services using SOLID principles, Python async, and type hints\nIntegrate and optimize SQL, NoSQL, and vector databases (Postgres, MongoDB, ChromaDB, Pinecone)\nRun LangGraph/Deep Agents workflows in production with checkpointing, persistence, and human-in-the-loop controls, backed by LLM observability and evaluation tooling (e.g., LangSmith, Langfuse)\nApply LLM safety guardrails (prompt-injection mitigation, PII handling, content moderation) in line with Banking, Insurance, and Healthcare compliance requirements\nStay current with emerging trends in GenAI, deep learning, and AI orchestration frameworks\nMinimum Qualifications\nBachelor's degree in Computer Science, Data Science, or related field\n3+ years of total professional experience, including:\n3+ years of hands-on Software Engineering experience in Python, FastAPI and relevant tech stack\n2+ years working specifically with GenAI and LLMs (GPT, Claude, LLaMA, etc.)\nTrack record of shipping production ML/AI products, with strong prompt-engineering skills, systems-level thinking, and the ability to diagnose and resolve production failures\nStrong software engineering background with expertise in OOP and SOLID principles\nProficiency in Python 3.11+ (async/await, type hints, modern Python patterns, strict type checking)\nExperience with agentic frameworks (LangChain, LangGraph, AutoGen, or similar)\nProven track record building production REST/WebSocket APIs and microservices\nExperience with message streaming platforms (Kafka, Pulsar, or similar)\nStrong knowledge of databases: SQL, NoSQL, and vector databases\nWorking knowledge of RAG pipelines (embeddings, chunking, retrieval) and LLM observability/evaluation tools (LangSmith, Langfuse, or similar)","description_format":"text","description_chars":3049,"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":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-01T20:44:33Z"},{"event":"close","at":"2026-10-03T01:09:12Z"}],"visa":[],"liveness":null,"pay":null,"html_url":"https://alion.io/job/exl-data-scientist-5","json_url":"https://alion.io/job/exl-data-scientist-5.json","meta":{"generated_at":"2026-10-06T03:12:30Z","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","counted_by":"address","units_charged":1,"used_today":4710,"day_limit":5000,"remaining_today":290,"minute_limit":60,"resets_at":"2026-10-07T00:00:00Z"}},"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":38016},"rest":"https://alion.io/mcp/rest/get_company?id=38016"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fexl-data-scientist-5"},{"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%2Fexl-data-scientist-5"},{"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%2Fexl-data-scientist-5"},{"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/exl-data-scientist-5\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fexl-data-scientist-5"}]}