Date: 2026-06-23

Location: Singapore, , Singapore

Company: NCS

Job Requisition ID: REF1648D

Company Description

NCS is a leading AI Tech Services company. With a 15,000-strong team across the Asia Pacific, NCS scales its platforms and capabilities to provide clients with greater agility and AI expertise across a range of Industries. Embracing a strong ecosystem of global partners, NCS transforms technology services delivery combining AI with digital resilience to drive real business impact. NCS is a subsidiary of the Singtel Group.

Job Description

What will you do?

Technical Delivery

Own end-to-end delivery of AI workstreams: from requirements through data preparation, modelling, integration, testing, and production handover
Develop agentic applications including RAG pipelines, prompt-engineered agents, and agentic workflows using LangChain, LlamaIndex, LangGraph, or plain Python
Build on top of GenAI application stacks including LLM orchestration, observability (Langfuse, Braintrust), guardrails, and LLM gateway patterns (LiteLLM, Portkey)
Implement multi-agent orchestration layer: event routing, resource locking, inter-agent handoff contracts, prompt caching, and shared state management
Implement agentic design patterns including workflow evaluation, LLM-as-Judge, and AI red teaming
Adopt Model Context Protocol (MCP) and Agent-to-Agent (A2A) Protocol as foundational extension mechanisms, enabling agents to operate safely across enterprise ecosystems
Work with AI Solution Architect and Business Analysts on benchmarking and golden-set compilation for agent evaluation
Implement effective RAG architectures: chunking strategies, embedding selection, vector store configuration (Qdrant, Milvus, pgvector), hybrid search, and reranking
Build and maintain evaluation harnesses measuring correctness, faithfulness, latency, and safety. Run continuous LLM-as-Judge evaluation on production traces
Write clean, maintainable Python; participate in code reviews; contribute to shared AI platform libraries

OSS Integration & Data Engineering

Implement REST, NETCONF/YANG, SNMP trap ingestion, and gNMI streaming telemetry integrations connecting agents to NMS and EMS systems
Build ServiceNow integrations for ticket read/write, triage updates, change record queries, and human-in-the-loop approval workflow triggers for the Execution Agent
Build the alarm and telemetry data normalisation pipeline converting multi-vendor OSS data into agent-consumable schemas
Implement Kafka or equivalent event streaming consumers delivering real-time alarm data to the Alarm Correlation and Ticket Triaging agents
Work with data and integration engineers to normalise multi-vendor, multi-format network telemetry into consistent schemas the agents can reason over

Safety, Guardrails & Risk

Implement guardrail architectures: hard limits, soft limits with human confirmation flows, blast radius controls, and escalation logic
Assist the AI Solution Architect to assess blast radius for each agent — documenting worst-case impacts and designing specific mitigating controls
Implement and validate rollback procedures for all agent-initiated network actions, including automated rollback triggers based on post-execution KPI degradation
Work with QA engineers to design and test solutions via defined test cases, and review required improvements
Ensure all agent architectures comply with IMDA regulatory requirements, AIVerify framework requirements, InfoSec policies, and CMB change governance frameworks

Observability & Evaluation

Implement the Decision Audit Trail schema for all agents ensuring every decision is fully traceable, explainable, and available for post-incident review
Build the Agent Operations Dashboard for the NOC team: real-time agent status, decision volumes, accuracy metrics, and exception alerts
Define and implement the evaluation framework: factual, reasoning, tool-call, retrieval and planning accuracy, confidence thresholds, and human feedback capture
Implement continuous evaluation of production agent traces using LLM-as-Judge for quality and safety; design human evaluation sample process
Build drift detection mechanisms that alert the team when agent output quality degrades before it becomes an operational incident
Containerise and deploy agent services using Docker and CI/CD pipelines; manage staging and production deployments with rollback capability

Qualifications

The ideal candidate should possess:
Minimum 3 years of AI/ML engineering experience, with at least 1 year in production Agentic AI systems (not PoC or prototype-only)
Demonstrable experience building AI agents that call external tools, manage state, and operate in production environments with real operational consequences
Hands-on experience with LLM APIs (OpenAI, Anthropic Claude) or Open Source LLMs on vLLM (Qwen, Mistral, DeepSeek) in production — including prompt engineering, evaluation, and cost management
Experience building RAG pipelines with vector databases (Qdrant, Milvus, Pinecone, Weaviate, pgvector) in production, including hybrid search and reranking
Practical experience with at least one agentic AI framework: LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, or custom tool-calling
Strong Python — modular, testable, production-quality code. Proficiency with Git, CI/CD, Docker, and LLMOps practices
Full-stack awareness: REST APIs, front-end integration, data pipelines
Degree in Computer Science, Electrical Engineering, AI/ML, or related technical field

Highly Desirable

Experience with Telco, utilities, or other 24×7 critical infrastructure environments where AI system failures have direct operational consequences
Familiarity with OSS systems: NMS, EMS, network alarm management, NETCONF/YANG, or gNMI streaming telemetry
Experience with event streaming platforms: Apache Kafka, Pulsar, or equivalent
Experience integrating with ServiceNow REST API for ITSM data
Experience with AI observability tools: Langfuse, Braintrust, LangSmith, Weights & Biases, Prometheus/Grafana
Experience implementing AI systems subject to regulatory or formal risk governance frameworks (CMB, InfoSec review, audit requirements)
Familiarity with network automation platforms (Cisco NSO, Nokia CloudBand, ONAP) as agent integration targets
Familiarity with TM Forum frameworks including the Autonomous Network Maturity Model (L0–L5)
Cloud ML platform experience: AWS SageMaker, Azure ML, or Google Vertex AI

Qualifications & Certifications

Required: Degree in Computer Science, Electrical Engineering, AI/ML, or related technical field
Desirable: Professional certifications in Agentic AI development and architecting

Additional Information

Why Join NCS

Lead high-impact AI management consulting programs for major enterprises and public sector clients.

Shape enterprise strategies and governance frameworks that drive real transformation.

Work with a talented, multidisciplinary team in a collaborative environment.

Competitive compensation and strong professional development support.

We are driven by our AEIOU beliefs—Adventure, Excellence, Integrity, Ownership, and Unity—and we seek individuals who embody these values in both their professional and personal lives. We are committed to our Impact: Valuing our clients, Growing our people, and Creating our future.

Together, we make the extraordinary happen.

Learn more about us at ncs.co and visit our LinkedIn career site.

Scam Alert

We are aware of fraudulent job offers and impersonations of NCS recruiters. Phishing emails using convincing-looking but fake addresses are also commonly used to trick you into thinking that they come from official NCS sources.

Please note that all official communications from NCS Group will only be sent from verified corporate email addresses. Always check that the sender’s email address ends with the genuine NCS domain, @ncs.com.sg and beware of extra letters, symbols or misspellings. When in doubt, verify the sender’s identity by contacting us at reachus@ncs.com.sg.

.jobdetail-video-MRD9fnMYzdE { background-image: url(https://img.youtube.com/vi/MRD9fnMYzdE/default.jpg) }