Gen AI Architect with SAP
10+ years
New Jersey, United States
$175k - $205k/year
Full-time
Remote
1 month ago
About the role
Role: Gen AI Architect with SAP
Location: Raritan - New Jersey - USA.
Domain: SAP
Reporting to: Vice President of Data & Analytics.
Key responsibilities
Required qualifications
Deliverables & artifacts
Benefits/perks listed below may vary depending on the nature of your employment with LTIMindtree (“LTIM”):
Benefits and Perks :
The range displayed on each job posting reflects the minimum and maximum salary target for the position across all US locations. Within the range, individual pay is determined by work location and job level and additional factors including job-related skills, experience, and relevant education or training. Depending on the position offered, other forms of compensation may be provided as part of overall compensation like an annual performance-based bonus, sales incentive pay and other forms of bonus or variable compensation.
Disclaimer : The compensation and benefits information provided herein is accurate as of the date of this posting.
LTIMindtree is an equal opportunity employer that is committed to diversity in the workplace. Our employment decisions are made without regard to race, color, creed, religion, sex (including pregnancy, childbirth or related medical conditions), gender identity or expression, national origin, ancestry, age, family-care status, veteran status, marital status, civil union status, domestic partnership status, military service, handicap or disability or history of handicap or disability, genetic information, atypical hereditary cellular or blood trait, union affiliation, affectional or sexual orientation or preference, or any other characteristic protected by applicable federal, state, or local law, except where such considerations are bona fide occupational qualifications permitted by law.
Location: Raritan - New Jersey - USA.
Domain: SAP
Reporting to: Vice President of Data & Analytics.
Key responsibilities
- Develop AI solutions in SAP ecosystem - design and build and operate the Control Plane components: Master Orchestrator, API Gateway, Agent Gateway(s), and Agent Lifecycle Manager.
- Implement reliable, scalable event-driven workflows using the central event bus (Kafka) and define topic structure, retention, and partitioning strategy.
- Design and operate agent runtimes and sandboxes (deployment, isolation, secrets distribution, agent versioning).
- Build and maintain the Agent Registry, Agent Marketplace, and Agent intake/approval flows, integrating with a policy/approval engine for governed onboarding.
- Integrate and manage knowledge stores: vector DB, knowledge graph, search index, and object store. Define retention, encryption, and access patterns.
- Implement secure secrets management and policy enforcement (HashiCorp Vault or equivalent, GovernAI/policy engine), and ensure auditability into SIEM/audit log.
- Build secure connectors to external tooling via an MCP Gateway (issue trackers, test automation, process modeling, RPA, ERPs) and manage multi-protocol agent integrations (gRPC, REST, webhooks, A2A).
- Implement observability: metrics, traces, logs, dashboards (Grafana), and set SLOs/SLA monitoring for platform services and agents.
- Define and maintain deployment pipelines, automated testing, and release processes for platform services and agent images (CI/CD).
- Produce architecture and runbooks, own operational playbooks for incident response, and mentor other engineers on best practices for secure agent development.
- Collaborate with security, compliance, and product teams to define and implement governance, RBAC, approval flows, and chargeback/usage reporting.
- Define metrics (accuracy, grounding, tool‑use correctness, latency, cost), implement regression testing, golden datasets, and drift detection across agent and model versions
- Configure confidence thresholds, approvals, and escalation paths; capture SME feedback and user signals to continuously improve agent behavior.
- Manage prompt/model versioning, approval flows, A/B or canary releases, rollback strategies, and enforce runtime policies for safe and compliant agent execution.
Required qualifications
- 5+ years experience building and operating distributed platform or infrastructure services (platform engineering, SRE, or backend engineering).
- Strong production experience with event-driven architectures and messaging systems (Kafka or equivalent).
- Proficiency deploying and operating services on Kubernetes or similar container platforms.
- Experience with design and implementation of API Gateways and microservices (REST/gRPC).
- Hands-on experience Python programming language used for orchestration/microservices.
- Experience with secrets management and enterprise policy enforcement (HashiCorp Vault or equivalent).
- Solid experience with observability tooling and tracing (Prometheus/Grafana).
- Experience with SQL and NoSQL stores (Postgres, DynamoDB, Redis) and object storage (S3).
- Strong understanding of security best practices, RBAC, audit logging and compliance considerations for enterprise systems.
- Excellent verbal and written communication skills; experience working cross-functionally with product and security teams.
- Experience with vector databases or embedding pipelines (Qdrant, Milvus, Pinecone or similar) and knowledge graph technologies (neo4j or RDF stores).
- Experience with OpenSearch/Elasticsearch for indexing and search.
- Familiarity with LLM integration patterns and RAG (retrieval-augmented generation) architectures.
- Experience building policy engines or governance tooling (e.g., OPA, custom policy frameworks).
- Familiarity with enterprise SSO/AD integration and identity federation.
- Experience integrating toolchains via MCP-like gateway patterns and working with 3rd-party tooling (Jira, SAP Signavio, test automation frameworks).
- Prior experience in regulated environments (GDPR, HIPAA) or large enterprise governance programs.
- Experience owning platform SLAs and chargeback/reporting systems.
- Hands‑on experience with LLM/agent evaluation frameworks, including automated testing, SME review loops, quality baselining, and performance drift monitoring.
- Proven experience implementing HITL systems for AI validation, exception handling, and enterprise decision augmentation.
- Strong understanding of model, prompt, and agent governance, including controlled rollouts, policy enforcement, responsible AI risks, and cost/token optimization.
Deliverables & artifacts
- Architecture diagrams and sequence flows for critical workflows.
- CI/CD pipelines and deployment manifests (Helm).
- Runbooks
- Automated tests for orchestration logic and integration adapters.
- Documentation for engineering teams on Agent development and onboarding.
- Agent evaluation scorecards and dashboards tracking quality, HITL override rates, latency, and inference cost.
- HITL workflow designs, escalation runbooks, and feedback incorporation mechanisms.
- Model and prompt governance documentation covering versioning, promotion criteria, rollback, and audit evidence.
Benefits/perks listed below may vary depending on the nature of your employment with LTIMindtree (“LTIM”):
Benefits and Perks :
- Comprehensive Medical Plan Covering Medical, Dental, Vision
- Short Term and Long-Term Disability Coverage
- 401(k) Plan with Company match
- Life Insurance
- Vacation Time, Sick Leave, Paid Holidays
- Paid Paternity and Maternity Leave
The range displayed on each job posting reflects the minimum and maximum salary target for the position across all US locations. Within the range, individual pay is determined by work location and job level and additional factors including job-related skills, experience, and relevant education or training. Depending on the position offered, other forms of compensation may be provided as part of overall compensation like an annual performance-based bonus, sales incentive pay and other forms of bonus or variable compensation.
Disclaimer : The compensation and benefits information provided herein is accurate as of the date of this posting.
LTIMindtree is an equal opportunity employer that is committed to diversity in the workplace. Our employment decisions are made without regard to race, color, creed, religion, sex (including pregnancy, childbirth or related medical conditions), gender identity or expression, national origin, ancestry, age, family-care status, veteran status, marital status, civil union status, domestic partnership status, military service, handicap or disability or history of handicap or disability, genetic information, atypical hereditary cellular or blood trait, union affiliation, affectional or sexual orientation or preference, or any other characteristic protected by applicable federal, state, or local law, except where such considerations are bona fide occupational qualifications permitted by law.
Skills
IT Services and IT Consulting