{"id":555781,"url":"https://alion.io/job/clario-lead-data-engineer-genai-llm-applications","title":"Lead Data Engineer (GenAI / LLM Applications)","company":{"id":8692,"name":"Clario","domain":"clario.com","url":"https://alion.io/company/clario","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"A","score":91,"open_postings":10,"ghost_share":0,"stale_share":0.3,"repost_share":0.1,"time_to_fill_p50_days":27,"computed_at":"2026-11-03T05:54:40Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"lead","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":26000,"max_usd":67000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":47},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AG Grid","optional":false},{"name":"Airflow","optional":false},{"name":"Amazon EC2","optional":false},{"name":"Amazon S3","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"AWS Lambda","optional":false},{"name":"CI/CD","optional":false},{"name":"Copilot","optional":false},{"name":"Django","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Flask","optional":false},{"name":"Git","optional":false},{"name":"LangChain","optional":false},{"name":"LLM","optional":false},{"name":"MS SQL","optional":false},{"name":"NumPy","optional":false},{"name":"Plotly","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Power BI","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Snowflake","optional":false},{"name":"SQL","optional":false},{"name":"Confluence","optional":true},{"name":"JavaScript","optional":true},{"name":"Jira","optional":true},{"name":"Microsoft Teams","optional":true}],"status":"live","first_seen_at":"2026-09-08T21:20:42Z","employer_posted_date":"2026-10-12","last_verified_at":"2026-11-03T12:52:50Z","board_verified":true,"closed_at":null,"days_open":55,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":55},"description":"We are looking for a skilled and motivated Lead Engineer to join our Data Science and Delivery group at Clario, a part of Thermo Fisher Scientific. This role combines software development, data engineering, and analytical problem-solving to design, build, and maintain scalable data platforms that support clinical trial operations and business intelligence. You will work across the full software development lifecycle (SDLC)-from requirements gathering through production support-collaborating closely with data scientists, analysts, product managers, and engineering teams to deliver high-quality, data-driven solutions.\nWhat We Offer\nCompetitive compensation aligned with local market practices\n\nComprehensive health and wellness benefits\n\nPaid time off and company holidays\n\nOpportunities for professional development, learning, and career growth\n\nThe flexibility of working from Bangalore or remotely within India, while collaborating with global teams\n\nWhat You’ll Be Doing\nDesign, develop, and maintain scalable software architectures and data pipelines that integrate with analytical and operational systems.\n\nWrite clean, reusable, and well-tested Python code using frameworks such as Flask and related libraries.\n\nLeverage AI-assisted development tools, including GitHub Copilot and LangChain, to design, build, and integrate LLM-powered solutions such as retrieval-augmented generation (RAG) pipelines, intelligent agents, and automated workflows using AWS Bedrock or similar services.\n\nDevelop and optimize complex SQL across Oracle, MS SQL Server, PostgreSQL, and Snowflake, including procedures, functions, views, analytical functions, and dynamic SQL.\n\nDesign and implement ETL pipelines using Snowflake and related data processing technologies.\n\nImplement scheduling and orchestration using Apache Airflow or similar workflow orchestration frameworks.\n\nEstablish and maintain data quality frameworks, versioning, and governance practices to ensure data reliability, integrity, and compliance.\n\nDevelop and maintain data architectures and models for both structured and unstructured data sources.\n\nTroubleshoot production issues and drive continuous improvement in software quality, performance, and reliability.\n\nDeploy, manage, and support solutions on AWS, including storage, compute, and pipeline services.\n\nCreate source-to-target mappings and support data and code migration initiatives.\n\nPartner with stakeholders to gather requirements, translate business needs into technical solutions, and produce clear, well-structured documentation.\n\nCollaborate with product managers, analysts, and cross-functional teams to deliver data-driven insights and reporting using tools such as Plotly and Power BI.\n\n What We Look For\nBachelor’s or higher degree in Computer Science, Information Technology, or a related technical field.\n\n5+ years of professional experience in software engineering, data engineering, or data-focused development roles.\n\nStrong proficiency in Python, including frameworks and libraries such as Django or Flask, pandas, NumPy, Plotly, and ag-Grid.\n\nStrong SQL expertise with Oracle, MS SQL Server, PostgreSQL, and/or Snowflake.\n\nProven experience writing complex SQL, including analytical and window functions, subqueries, all join types, DML/DDL/TCL statements, CASE expressions, and performance tuning.\n\nWorking knowledge of cloud platforms, with a preference for AWS (S3, EC2, Secrets Manager, Bedrock, Lambda).\n\nExperience using AI-assisted development tools and frameworks such as GitHub Copilot and LangChain for building LLM-powered applications and workflows.\n\nExperience with Git-based version control systems and CI/CD pipelines.\n\nFamiliarity with data modeling concepts for both structured and unstructured data.\n\nStrong analytical thinking, problem-solving abilities, and communication skills.\n\nWillingness to work across all phases of the SDLC, including requirements gathering, design, development, deployment, and production support.\n\nPreferred experience includes exposure to the clinical trial lifecycle or clinical data management, data visualization tools (Plotly, Power BI), front-end technologies (HTML5, CSS3, JavaScript), collaboration tools (Jira, Confluence, Microsoft Teams), and hands-on data analysis or data cleansing using programming languages, SQL, and Excel.\n\nAt Clario, our purpose is to transform lives by unlocking better evidence. It’s a cause that unites and inspires us. It’s why we come to work-and how we empower our people to make a positive impact every day. Whether you’re starting your clinical data career or building long-term expertise, your work helps bring life-changing therapies to patients faster.","description_format":"text","description_chars":4688,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":["Professional development"],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Clinical Trial Services (CRO)","CRO & CDMO Services","Clinical Trial Software"],"lifecycle":[{"event":"open","at":"2026-09-08T21:20:42Z"}],"visa":[],"liveness":{"score":24,"band":"cold","label":"Long shot","p_open":1,"p_active":0.678,"p_room":0.35,"age_days":55,"expected_fill_days":27,"reasons":["conf:3","velocity","win:tail"],"computed_at":"2026-11-03T05:54:40Z"},"pay":null,"html_url":"https://alion.io/job/clario-lead-data-engineer-genai-llm-applications","json_url":"https://alion.io/job/clario-lead-data-engineer-genai-llm-applications.json","meta":{"generated_at":"2026-11-03T18:36:55Z","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":378,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-04T00:00:00Z"}},"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":8692},"rest":"https://alion.io/mcp/rest/get_company?id=8692"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fclario-lead-data-engineer-genai-llm-applications"},{"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%2Fclario-lead-data-engineer-genai-llm-applications"},{"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%2Fclario-lead-data-engineer-genai-llm-applications"},{"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/clario-lead-data-engineer-genai-llm-applications\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclario-lead-data-engineer-genai-llm-applications"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":555781}},{"tool":"search_jobs","arguments":{"company":"clario.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":555781},"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"}}