Must Have Technical/Functional Skills
Establishing enterprise GenAI/ML architecture from discovery PoC pilot production, ensuring scalability, security, reliability, and measurable business value. Experience in LLM, AI/ML Concepts.
Partner with business, product, risk, and ops leaders to identify/prioritize AI use cases in payments, define success metrics, and build value/feasibility assessments.
Design solution blueprints and produce HLD/LLD + Lucid architecture diagrams, covering integrations, NFRs, data flows, and deployment/run operations.
Experience with On Prem as well as Cloud-native GenAI solutions (Google will be a Plus) using Vertex AI + Gemini, integrating with BigQuery/Cloud Storage and scalable runtime options (Cloud Run/GKE).
Establish Prompt Engineering standards: system/tool prompts,few shot patterns, structured outputs (JSON schemas), guardrails, prompt versioning, and automated regression testing.
Experience with Agentic AI frameworks like LangChain, LangGraph and LangSmith.
Architect advanced RAG systems: ingestion pipelines, chunking/metadata strategy, hybrid retrieval + reranking, citation/grounding, and continuous quality evaluation.
Roles & Responsibilities
Lead end to end enterprise GenAI/ML architecture from discovery PoC pilot production, ensuring scalability, security, reliability, and measurable business value.
Partner with business, product, risk, and ops leaders to identify/prioritize AI use cases in payments, define success metrics, and build value/feasibility assessments.
Design solution blueprints and produce HLD/LLD + Lucid architecture diagrams, covering integrations, NFRs, data flows, and deployment/run operations.
Experience with On Prem as well as Cloud-native GenAI solutions (Google will be a Plus) using Vertex AI + Gemini, integrating with BigQuery/Cloud Storage and scalable runtime options (Cloud Run/GKE).
Establish Prompt Engineering standards: system/tool prompts, few shot patterns, structured outputs (JSON schemas), guardrails, prompt versioning, and automated regression testing.
Experience with Agentic AI frameworks like LangChain, LangGraph and LangSmith.
Architect advanced RAG systems: ingestion pipelines, chunking/metadata strategy, hybrid retrieval + reranking, citation/grounding, and continuous quality evaluation.
Design vector data models and retrieval optimization (embeddings, indexing, freshness, governance) to support high accuracy, low latency enterprise knowledge experiences.
Lead AI Agent design: tool/function calling, planning/execution loops, memory strategies, and human in the loop approvals for controlled automation.
Build Agentic Workflow orchestration (multi step business processes) with clear role boundaries, fail safes, escalation paths, and auditability.
Enable A2A (Agent to Agent) collaboration patterns-specialized agents (retrieval, policy, fraud signals, customer comms) coordinated via a central orchestrator.
Define and govern MCP (Model Context Protocol) integrations to standardize tool connectivity, context injection, authorization, and safe tool execution across enterprise services.
Drive MLOps/LLMOps practices: CI/CD, prompt/model versioning, automated evaluations, drift/quality monitoring, cost controls, canary releases, and rollback strategies.
Embed payments grade security, privacy, and compliance: IAM least privilege, encryption/KMS, secrets management, PII controls, threat modeling, and audit evidence.
Collaborate with internal teams and technology partners to ensure smooth implementation, performance tuning, and production readiness across environments.
Mentor teams and evangelize an AI engineering culture through reusable reference architectures, best practices, knowledge sharing, and technical governance.
Salary Range: $100,000 to $130,000 per year