Back to jobs
New

Sr. AI Engineer - Data Pipelines & Context Systems

Bangalore

At Reltio®, an SAP Company, we believe data should fuel your success in the enterprise AI era. Our  Context Intelligence Platform turns fragmented data into a trusted, connected context so AI agents and systems can act with expert-level judgement at enterprise scale. Reltio’s cloud-native SaaS platform harmonizes, unifies, and governs data across sources and formats—including unstructured data—in real time, turning them into data assets that can be mobilized in milliseconds to any application, user, or AI agent. Trusted by more than 200 of the world’s largest brands across industries such as life sciences, financial services, healthcare, and technology, we fuel frictionless operations and help enterprises accelerate  innovation and reduce risk.

At Reltio, our values guide everything we do. With an unyielding commitment to prioritizing our “Customer First”, we strive to ensure their success. We embrace our differences and are “Better Together” as One Reltio. We are always looking to “Simplify and Share” our knowledge when we collaborate to remove obstacles for each other. We hold ourselves accountable for our actions and outcomes and strive for excellence. We “Own It”. Every day, we innovate and evolve, so that today is “Always Better Than Yesterday”. If you share and embody these values, we invite you to join our team at Reltio and contribute to our mission of excellence.

Reltio has earned numerous awards and industry and analyst recognition for our technology, our culture and our people. Reltio was founded on a distributed workforce and offers flexible work arrangements to help our people manage their personal and professional lives. If you’re ready to work on unrivaled technology where your desire to be part of a collaborative team is met with a laser-focused mission to enable digital transformation with connected data, let’s talk!

Job Summary: 

We are building a highly specialized Enterprise AI Hub to engineer the "Reltio Brain" - a Context Intelligence Operating System that transforms fragmented institutional knowledge into governed, autonomous action. As the Sr. AI Engineer (Data Pipelines & Context Systems), you will build the governed data, context, and tooling layer that allows Reltio AI systems and embedded AI Business Partners to work safely across enterprise knowledge. This role is centered on data pipeline management, context organization, retrieval quality, and model/tool harnesses. You will connect structured and unstructured sources, maintain freshness and access controls, and create reusable MCP/API-style tools that let AI workflows use the right data with clear provenance. This is not primarily a front-end/UI role. You may build lightweight internal surfaces for review, administration, and workflow handoffs, but the center of gravity is the data and context foundation behind those experiences: ingestion, indexing, permissions, source trust, evaluation, and operational reliability.

Job Duties and Responsibilities:

AI Data Pipeline & Context Architecture

  • Design and implement production-grade pipelines that ingest, normalize, enrich, and synchronize structured and unstructured enterprise data from sources such as Reltio/MDM, Google Workspace, Slack, Jira/Confluence, transcripts, product systems, and operational datasets.
  • Build patterns for incremental indexing and vector updates so AI systems can refresh only what changed while preserving lineage, permissions, and source metadata.
  • Model context boundaries across personal, team, departmental, and enterprise layers so AI systems understand where information came from, why it matters, and who can access it.

Governed MCP/API Tooling:

  • Build secure MCP/API-style tools and services that expose enterprise data and actions to LLM workflows with clear schemas, guardrails, and audit trails.
  • Implement OAuth/SSO, RBAC/ABAC, tenant boundaries, and server-side permission checks so retrieval and tool execution respect enterprise access controls.
  • Create reusable connectors and adapters for AI Business Partner workflows, starting with pragmatic first versions that can be operated, handed off, and improved.

Retrieval, Indexing & Source Trust:

  • Design RAG/retrieval systems that combine semantic search, keyword search, metadata filters, reranking, and structured queries to assemble reliable context.
  • Define chunking, embedding, tagging, and provenance strategies that make responses traceable back to source documents, records, transcripts, or systems of record.
  • Monitor freshness, data quality, duplicate or stale content, hallucination risk, and missing-context failure modes.

Model / Tool Harnesses & Evaluation:

  • Build harnesses for testing prompts, retrieval pipelines, tool calls, structured outputs, and agentic workflows before they are used in production.
  • Create evaluation datasets, acceptance criteria, observability, and regression checks for context quality, tool accuracy, latency, cost, and safety.
  • Use modern AI coding assistants such as Codex, Claude Code, and Cursor to accelerate implementation while maintaining engineering discipline, security, and review standards.

Human-in-the-Loop Operations:

  • Build review, approval, rollback, and exception-handling workflows for high-impact AI actions and sensitive data usage.
  • Create admin and debugging tools that let operators inspect source context, tool decisions, access rules, and pipeline status.
  • Partner with AI Business Partners, Security, Product, Data, and Engineering teams to translate business workflows into durable, governed AI capabilities.

Reusable Enterprise Patterns:

  • Identify technical components that can be reused by Enterprise AI, Product, and partner teams, including connectors, context services, evaluation harnesses, and governance patterns.
  • Document implementation patterns clearly enough for stakeholders and engineering teams to understand, operate, and extend them.
  • Bootstrap first versions in partnership with existing P&T and Enterprise AI teams, then help define the path to ownership, scale, and product alignment.

Skills You Must Have:

  • 5+ years of software, backend, data platform, or AI engineering experience building production data systems, internal platforms, or AI-enabled systems.
  • Strong proficiency in Python and/or TypeScript/Node.js, with experience designing APIs, services, async jobs, data models, and integrations.
  • Hands-on experience with data ingestion, transformation, synchronization, and operational data pipelines across multiple source systems.
  • Practical experience with RAG/retrieval systems, including embeddings, vector/search stores, chunking, metadata filtering, hybrid search, reranking, citations/source provenance, and incremental updates.
  • Experience building with LLM tool calling, agents, structured outputs, schema validation, and MCP-style or function/API-based tool layers.
  • Strong understanding of enterprise identity, access control, and data governance, including OAuth/SSO, RBAC/ABAC, privacy, auditability, and secure handling of sensitive information.
  • Ability to design evaluation harnesses and operational checks for retrieval quality, model/tool accuracy, latency, cost, freshness, and regression risk.
  • Strong judgment with AI-assisted development tools such as Codex, Claude Code, and Cursor, using them to accelerate delivery while validating generated code and decisions.
  • Clear communication with technical and business stakeholders; able to explain data flow, context quality, risk, and tradeoffs in practical language.

Skills That Are Nice to Have:

  • Familiarity with Reltio, MDM, master data management, data governance, knowledge graphs, or customer/product data domains.
  • Experience with enterprise search/vector infrastructure such as OpenSearch, Pinecone, pgvector, Bedrock Knowledge Bases, or similar platforms.
  • Experience integrating with Google Workspace, Slack, Jira, Confluence, Salesforce, NetSuite, data warehouses, or other enterprise platforms.
  • Front-end experience with React, Next.js, Vercel, or internal admin/review tools; enough to build simple surfaces that expose pipeline state and support human review.
  • Experience with workflow orchestration, approval systems, event-driven architectures, queues, batch/stream processing, Docker/Kubernetes, infrastructure as code, or observability stacks.
  • Experience in a 500-2,000 employee SaaS company or similar scale.

 

Reltio is proud to be an equal opportunity workplace. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or Veteran status. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. Reltio is committed to working with and providing reasonable accommodation to applicants with physical and mental disabilities.

Create a Job Alert

Interested in building your career at Reltio? Get future opportunities sent straight to your email.

Apply for this job

*

indicates a required field

Resume/CV*

Accepted file types: pdf, doc, docx, txt, rtf

Cover Letter

Accepted file types: pdf, doc, docx, txt, rtf

Voluntary Self-Identification

For government reporting purposes, we ask candidates to respond to the below self-identification survey. Completion of the form is entirely voluntary. Whatever your decision, it will not be considered in the hiring process or thereafter. Any information that you do provide will be recorded and maintained in a confidential file.

As set forth in Reltio’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law.

Select...
Select...
Race & Ethnicity Definitions

If you believe you belong to any of the categories of protected veterans listed below, please indicate by making the appropriate selection. As a government contractor subject to the Vietnam Era Veterans Readjustment Assistance Act (VEVRAA), we request this information in order to measure the effectiveness of the outreach and positive recruitment efforts we undertake pursuant to VEVRAA. Classification of protected categories is as follows:

A "disabled veteran" is one of the following: a veteran of the U.S. military, ground, naval or air service who is entitled to compensation (or who but for the receipt of military retired pay would be entitled to compensation) under laws administered by the Secretary of Veterans Affairs; or a person who was discharged or released from active duty because of a service-connected disability.

A "recently separated veteran" means any veteran during the three-year period beginning on the date of such veteran's discharge or release from active duty in the U.S. military, ground, naval, or air service.

An "active duty wartime or campaign badge veteran" means a veteran who served on active duty in the U.S. military, ground, naval or air service during a war, or in a campaign or expedition for which a campaign badge has been authorized under the laws administered by the Department of Defense.

An "Armed forces service medal veteran" means a veteran who, while serving on active duty in the U.S. military, ground, naval or air service, participated in a United States military operation for which an Armed Forces service medal was awarded pursuant to Executive Order 12985.

Select...

Voluntary Self-Identification of Disability

Form CC-305
Page 1 of 1
OMB Control Number 1250-0005
Expires 04/30/2026

Why are you being asked to complete this form?

We are a federal contractor or subcontractor. The law requires us to provide equal employment opportunity to qualified people with disabilities. We have a goal of having at least 7% of our workers as people with disabilities. The law says we must measure our progress towards this goal. To do this, we must ask applicants and employees if they have a disability or have ever had one. People can become disabled, so we need to ask this question at least every five years.

Completing this form is voluntary, and we hope that you will choose to do so. Your answer is confidential. No one who makes hiring decisions will see it. Your decision to complete the form and your answer will not harm you in any way. If you want to learn more about the law or this form, visit the U.S. Department of Labor’s Office of Federal Contract Compliance Programs (OFCCP) website at www.dol.gov/ofccp.

How do you know if you have a disability?

A disability is a condition that substantially limits one or more of your “major life activities.” If you have or have ever had such a condition, you are a person with a disability. Disabilities include, but are not limited to:

  • Alcohol or other substance use disorder (not currently using drugs illegally)
  • Autoimmune disorder, for example, lupus, fibromyalgia, rheumatoid arthritis, HIV/AIDS
  • Blind or low vision
  • Cancer (past or present)
  • Cardiovascular or heart disease
  • Celiac disease
  • Cerebral palsy
  • Deaf or serious difficulty hearing
  • Diabetes
  • Disfigurement, for example, disfigurement caused by burns, wounds, accidents, or congenital disorders
  • Epilepsy or other seizure disorder
  • Gastrointestinal disorders, for example, Crohn's Disease, irritable bowel syndrome
  • Intellectual or developmental disability
  • Mental health conditions, for example, depression, bipolar disorder, anxiety disorder, schizophrenia, PTSD
  • Missing limbs or partially missing limbs
  • Mobility impairment, benefiting from the use of a wheelchair, scooter, walker, leg brace(s) and/or other supports
  • Nervous system condition, for example, migraine headaches, Parkinson’s disease, multiple sclerosis (MS)
  • Neurodivergence, for example, attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder, dyslexia, dyspraxia, other learning disabilities
  • Partial or complete paralysis (any cause)
  • Pulmonary or respiratory conditions, for example, tuberculosis, asthma, emphysema
  • Short stature (dwarfism)
  • Traumatic brain injury
Select...

PUBLIC BURDEN STATEMENT: According to the Paperwork Reduction Act of 1995 no persons are required to respond to a collection of information unless such collection displays a valid OMB control number. This survey should take about 5 minutes to complete.