Agentic AI Engineer

Xora Innovation

Help design the foundational layer for LLM-powered AI features at Elemynt, an early-stage startup focused on applied intelligence. Engage in hands-on development across multiple model providers and frameworks.

Posted 8/2/2026full-timeSingapore • 🇸🇬 SingaporeMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and shipping production software, particularly in LLM and agent systems, with a strong focus on orchestration, retrieval systems, and observability. Proficient in Python and solid engineering practices, ensuring reliable and efficient workflows in fast-paced environments.

Highest-signal resume keywords

Python ProgrammingLLM Systems DevelopmentAgent OrchestrationRetrieval Systems EngineeringObservability Instrumentation

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Async CodeTypingTestingModular DesignCode ReviewStructured OutputsContext ManagementMemory ManagementHybrid SearchVector Databases

Soft Skills

Problem-SolvingAdaptabilityCollaboration

Tools & Technologies

Model ProvidersTracing ToolsEvaluation FrameworksVersion Control Systems

Certifications & Qualifications

Bachelor’s Degree in Computer ScienceMaster’s Degree in Computer Science

Industry Keywords

Production SoftwareAgent SystemsLLM EvaluationCost TrackingDebugging

Tech Stack

Tools & technologies

Python

About the role

Key responsibilities & impact

Build the provider abstraction that lets any workflow call, swap, or add a model provider by configuration, across commercial APIs and self-hosted endpoints, with structured-output validation, retries, and cost tracking.
Build the agent orchestration where a planning agent dispatches specialized sub-agents in parallel on a stateful framework, with durable checkpoints, conditional branching, and the context and memory management that keeps multi-step workflows coherent across long task horizons.
Build human-in-the-loop checkpoints so low-confidence or high-stakes steps route to a person before an agent proceeds.
Wrap existing platform capabilities as typed, registered tools the agents call, with a clean boundary between the agent layer and the systems it builds on.
Design retrieval end to end, from ingestion, embeddings, and chunking through hybrid search and reranking, and assemble the context that grounds each model call.
Build the prompt layer: versioned prompts, few-shot sets, and captured reasoning, so every change is tracked and every call is inspectable.
Expose agents and guardrailed model access as tools behind one integration point that backend services, the frontend, and notebooks all consume.
Instrument every model call, tool invocation, and agent run as traced spans with prompt, model, and tool lineage, so behavior and cost stay debuggable.
Build the evaluation framework, deterministic trace metrics alongside LLM-as-judge scoring for faithfulness, that gates changes and catches regressions before they ship.

Requirements

What you’ll need

Bachelor’s or Master’s degree in Computer Science or related engineering field, and 5+ years building and shipping production software, with real depth building LLM or agent systems in production.
Strong Python and solid engineering practice: async code, typing, testing, modular design, and code review, plus a track record of shipping systems others depend on.
Hands-on experience building agentic or LLM systems in production: orchestration loops, tool-calling, structured outputs, and context and memory management for reliable long-running workflows.
Experience working across multiple model providers behind a single abstraction, with routing, fallback, and a feel for the cost and latency trade-offs.
Experience building retrieval systems end to end: embeddings, chunking, hybrid search, reranking, and vector databases.
Experience with LLM evaluation and guardrails: building eval sets and harnesses, LLM-as-judge scoring, regression gating, and output-quality and safety checks.
Experience instrumenting LLM systems for observability: tracing model and tool calls, versioning prompts, and using traces to debug and improve real behavior.
Comfort owning ambiguous systems end to end in a fast-moving early-stage environment.

Benefits

Comp & perks

🌐 Worldwide ❌ Jobs You've Hidden ⭐️ Saved Jobs ✅ Applied Jobs ✉️ Email Alerts 👤 Account Xora Innovation Website LinkedIn All Job Openings 11 - 50 employees Founded 2019 💼 Consulting 🏥 Healthcare 📦 Logistics Consulting
Healthcare
Logistics Xora Innovation is a venture capital firm that partners with exceptional entrepreneurs in the deep tech space, focusing on transforming essential industries. Xora provides financial support and commitment to innovative companies that are building tomorrow's global infrastructure across three key sectors: Compute & Communications, Climate & Energy, and AI in Physical Industries. Agentic AI Engineer Job not on LinkedIn 🔥 1 hour ago 🏢🏡 Singapore – Hybrid ⏰ Full Time 🟡 Mid-level 🟠 Senior 🤖 AI Engineer Python Apply Now Find Hiring Managers Customize resume + cover letter Report problem ☆ Save ☑️ Mark as applied ❌ Hide 📋 Description
Build the provider abstraction that lets any workflow call, swap, or add a model provider by configuration, across commercial APIs and self-hosted endpoints, with structured-output validation, retries, and cost tracking.
Build the agent orchestration where a planning agent dispatches specialized sub-agents in parallel on a stateful framework, with durable checkpoints, conditional branching, and the context and memory management that keeps multi-step workflows coherent across long task horizons.
Build human-in-the-loop checkpoints so low-confidence or high-stakes steps route to a person before an agent proceeds.
Wrap existing platform capabilities as typed, registered tools the agents call, with a clean boundary between the agent layer and the systems it builds on.
Design retrieval end to end, from ingestion, embeddings, and chunking through hybrid search and reranking, and assemble the context that grounds each model call.
Build the prompt layer: versioned prompts, few-shot sets, and captured reasoning, so every change is tracked and every call is inspectable.
Expose agents and guardrailed model access as tools behind one integration point that backend services, the frontend, and notebooks all consume.
Instrument every model call, tool invocation, and agent run as traced spans with prompt, model, and tool lineage, so behavior and cost stay debuggable.
Build the evaluation framework, deterministic trace metrics alongside LLM-as-judge scoring for faithfulness, that gates changes and catches regressions before they ship. 🎯 Requirements
Bachelor’s or Master’s degree in Computer Science or related engineering field, and 5+ years building and shipping production software, with real depth building LLM or agent systems in production.
Strong Python and solid engineering practice: async code, typing, testing, modular design, and code review, plus a track record of shipping systems others depend on.
Hands-on experience building agentic or LLM systems in production: orchestration loops, tool-calling, structured outputs, and context and memory management for reliable long-running workflows.
Experience working across multiple model providers behind a single abstraction, with routing, fallback, and a feel for the cost and latency trade-offs.
Experience building retrieval systems end to end: embeddings, chunking, hybrid search, reranking, and vector databases.
Experience with LLM evaluation and guardrails: building eval sets and harnesses, LLM-as-judge scoring, regression gating, and output-quality and safety checks.
Experience instrumenting LLM systems for observability: tracing model and tool calls, versioning prompts, and using traces to debug and improve real behavior.
Comfort owning ambiguous systems end to end in a fast-moving early-stage environment. Apply Now 📊 Check your resume score for this job Improve your chances of getting an interview by checking your resume score before you apply. Check Resume Score Similar Jobs Forward Deployed AI Engineer 🕒 4 days ago Cloudera 1001 - 5000 💼 Consulting 🏥 Healthcare 📦 Logistics Website LinkedIn All Job Openings Hands-on AI Engineer building enterprise-grade AI applications using Cloudera's platform. Collaborating with clients to prototype and implement AI strategies in the workplace. 🏢🏡 Singapore – Hybrid 💰 $4.1M Venture Round on 2013-01 ⏰ Full Time 🟡 Mid-level 🟠 Senior 🤖 AI Engineer AI Support Engineer 🕒 July 22 OpenAI 201 - 500 🤖 Artificial Intelligence ☁️ SaaS 🏢 Enterprise Website LinkedIn All Job Openings AI Support Engineer resolving complex customer issues while collaborating with various teams at OpenAI. Building the first post-AGI support team to enhance customer experience. 🏢🏡 Singapore – Hybrid ⏰ Full Time 🟠 Senior 🔴 Lead 🤖 AI Engineer Python Switching AI Success Engineer 🕒 July 22 OpenAI 201 - 500 🤖 Artificial Intelligence ☁️ SaaS 🏢 Enterprise Website LinkedIn All Job Openings AI Success Engineer guiding organizations in deploying AI for business value. Leading technical relationships and driving customer success with OpenAI's platform. 🏢🏡 Singapore – Hybrid ⏰ Full Time 🟠 Senior 🔴 Lead 🤖 AI Engineer 🗣️🇨🇳 Chinese Required Switching AI/ML Architect 🕒 July 21 Red Hat 10,000+ employees 🏢 Enterprise Website LinkedIn All Job Openings AI/ML Architect responsible for designing production-ready architectural blueprints for enterprise AI workloads at Red Hat. Collaborating with clients while mentoring engineering colleagues in Singapore. 🏢🏡 Singapore – Hybrid 💰 Corporate Round on 1999-03 ⏰ Full Time 🟡 Mid-level 🟠 Senior 🤖 AI Engineer Ansible Kubernetes Python PyTorch Tensorflow Terraform Senior AI/ML Architect 🕒 July 21 Red Hat 10,000+ employees 🏢 Enterprise Website LinkedIn All Job Openings Senior AI/ML Architect designing enterprise-grade Kubernetes solutions as part of Red Hat's Singapore AI Center of Excellence. Leading architecture blueprints and providing strategic technical advice to clients. 🏢🏡 Singapore – Hybrid 💰 Corporate Round on 1999-03 ⏰ Full Time 🟠 Senior 🤖 AI Engineer Ansible Kubernetes Python PyTorch Tensorflow Terraform View More AI Engineer Jobs 🌐 Worldwide Built by Lior Neu-ner. I'd love to hear your feedback — Get in touch via DM or support@remoterocketship.com Search Search Jobs by country Search jobs by city Search jobs by job title Search entry-level jobs Search junior-level jobs Search senior-level jobs Search jobs by tech stack Search jobs by contract type Search remote internships Search remote part-time jobs Remote jobs Anywhere in the World Companies Hiring Anywhere in the World Companies Hiring Sales People Anywhere in the World Companies Hiring Software Engineers Anywhere in the World Resources Advice Tips for finding remote jobs Interview questions and answers Resume examples Cover letter examples Post a job Affiliates Is Remote Rocketship legit? Privacy policy Terms of service Job board SEO course Remote Job Search MasterClass AI Apply Copilot OpenClaw job finder Find jobs using your resume Jobs by Country Remote jobs anywhere in the world (Worldwide remote jobs) Remote jobs United States Remote jobs Australia Remote jobs Brazil Remote jobs Canada Remote jobs France Remote jobs Ireland Remote jobs Germany Remote jobs Netherlands Remote jobs Spain Remote jobs UK Popular Jobs Remote data analyst jobs Remote customer support jobs Remote executive assistant jobs Remote marketing jobs Remote product designer jobs Remote product manager jobs Remote project manager jobs Remote recruiter jobs Remote sales jobs Remote software engineer jobs Jobs by Type Remote full-time jobs Remote part-time jobs Remote contract jobs Remote internship jobs Remote entry-level jobs Remote jobs with no experience required Remote junior jobs (1-3 years of experience) Digital nomad jobs Remote jobs with no degree required Freelance remote jobs Temporary remote jobs Remote jobs hiring now Stay at home mom jobs