REF92857P_2026224137 - AI/ML Engineer - 4 to 8 years - Pune/Vizag (WFO)

WNS (Holdings) Limited (NYSE: WNS), is a leading Business Process Management (BPM) company. We combine our deep industry knowledge with technology and analytics expertise to co-create innovative, digital-led transformational solutions with clients across 10 industries. We enable businesses in Travel, Insurance, Banking and Financial Services, Manufacturing, Retail and Consumer Packaged Goods, Shipping and Logistics, Healthcare, and Utilities to re-imagine their digital future and transform their outcomes with operational excellence.We deliver an entire spectrum of BPM services in finance and accounting, procurement, customer interaction services and human resources leveraging collaborative models that are tailored to address the unique business challenges of each client. We co-create and execute the future vision of 400+ clients with the help of our 44,000+ employees.

We are seeking a highly skilledAgentic AI Engineer to build and deploymulti-agent, goal-driven automation fordocument-heavy logistics workflows. The role owns theend-to-end agent lifecycle: fromemail/document ingestion toorchestrated workflow execution,system integrations (TMS/BL platforms), and a robusthuman-in-the-loop (HITL) + audit layer required for regulated shipping documentation.

This is not a “model-only” ML role. You will engineerproduction-grade agentic workflows where agents do the work, the orchestrator decides what runs, exceptions are routed correctly, and every action is traceable.

Key Responsibilities

1) Agentic Workflow Orchestration (Core)

• Design and implementmulti-agent architectures (classification, extraction, validation, customer follow-up, drafting, amendments, release) under aunified orchestrator that routes tasks, handles retries, manages state, and enforces guardrails.
• Buildcase/task management for shipment documentation workflows: SLA prioritization, escalation rules, exception categories, and queue-based operations (shadow → assist → auto).
• Implementconfidence-driven automation (auto-run vs escalate vs stop) and structured fallbacks when upstream data or system access is limited.

2) Enterprise Integration (TMS / BL / eBL / Content Systems)

• Build secure integrations to enterprise systems usingREST/SOAP APIs where available; design pragmatic fallbacks (file-drop, staging UI, controlled automation) when direct APIs are constrained (e.g., Citrix-hosted systems).
• Integrate with:
  • Outlook/email ingestion and communication loops (request missing info, reminders, threaded responses).
  • Digiview / content repositories for archiving and retrieval of instruction/amendment emails and supporting documents.
  • BL platforms / eBL networks as required by process design (draft → review → release).
• Create robust integration patterns: idempotency, deduplication, rate limiting, secure service accounts, sandbox/testing modes.

3) GenAI + RAG for SOP-grounded Reasoning

• Implement LLM-powered capabilities forclassification, extraction, SOP-grounded validations, and structured decision support usingRAG (vector DB), prompt engineering, and context management.
• Optimizetoken usage and response structure for cost-efficient, scalable throughput.

4) Document Intelligence & Data Pipelines

• Builddocument handling pipelines (OCR/PDF parsing, table extraction, field normalization) for SI/draft/amendment content, including multilingual and semi-structured formats.
• Engineer data pipelines to support continuous improvement: training data capture, labeling workflows, replay harness, and error analysis.

5) Human-in-the-Loop (HITL) Console, Audit & Controls

• Build aHITL review/approval layer (draft BL review, exception resolution, amendment approvals) with role-based access controls and supervisor capabilities—treated as a peer system with its own logs and controls.
• Implement a fullaudit trail: every automated/manual action logged with timestamp, actor, input evidence, decision path, and output artifacts.
• Ensure compliance-ready traceability for shipping documentation processes.

6) ML Ops / LLM Ops & Production Reliability

• Deploy and operate the solution usingcontainerization (Docker/Kubernetes), CI/CD pipelines, monitoring, alerting, and rollback strategies.
• Monitor and optimize performance (latency, cost, failure modes), ensure safe degradation, and maintain high availability.

• 4–8+ years in software engineering / automation / AI engineering roles with demonstrated delivery of production systems.
• Proven experience withagentic AI orchestration frameworks (e.g., LangChain or similar orchestration frameworks) and building multi-step autonomous workflows.
• Strong experience integrating enterprise systems viaAPIs (REST/SOAP) and designing fallbacks for restricted environments.

Technical Skills

• Python proficiency and strong engineering fundamentals (design patterns, data structures, Git).
• Experience withvector databases and RAG patterns (Pinecone/Weaviate/Milvus or similar).
• Document processing expertise: OCR/PDF parsing, extraction pipelines, automation scripting.
• Cloud deployment experience onAWS/Azure/GCP and production-grade operational practices.
• Containerization & CI/CD:Docker, Kubernetes, pipelines, observability.

Production & Governance

• Hands-on experience implementingHITL workflows, audit logging, RBAC, and operational dashboards.
• Ability to build safe autonomous systems: confidence gating, policy constraints, replay testing.

Preferred / Good-to-Have (Strong Differentiators)

• Prior work inlogistics/shipping documentation workflows (SI/BL/HBL, amendments, trade-lane SOPs).
• Experience with workflow/case management platforms or orchestration engines beyond agent frameworks.
• Experience with RPA/UI automation as fallback in constrained environments (Citrix-style).
• Familiarity with secure enterprise integration patterns: service accounts, secrets management, network controls.