Makro PRO

Makro PRO is an exciting new digital venture by the iconic Makro. Our proud purpose is to build a technology platform that will help make business possible for restaurant owners, hotels, and independent retailers, and open the door for sellers. We welcome bold, energetic, and thoughtful people who share our belief in collaboration, diversity, excellence, and putting customers at the heart of our work. Clear focus Diverse Workplace (Our members are from around the world!) Non-hierarchical and agile environment Growth opportunity and career path

AI Engineer - Agent Development

Location

Thailand

Posted

17 days ago

Salary

0

Seniority

Mid Level

No structured requirement data.

Job Description

AI Engineer - Agent Development

Makro PRO

Role Description The AI Engineer builds production agents end-to-end on an AI-native retail decisioning platform. The role includes: - Prompt design - Tool definitions - Multi-step workflows on the agent runtime (LangGraph, CrewAI, or chosen framework) - Evaluation harnesses (golden sets, regression gates, multi-step replay) - Human-in-the-loop gate integration - Per-agent cost optimisation Remote candidates outside of Thailand are welcome to apply. Qualifications - Bachelor's or Master's degree in Computer Science, AI / ML, or a related discipline - 5+ years software engineering experience - 2+ years shipping LLM-based or agentic systems to production - Production agent or multi-step LLM workflow experience — LangGraph, CrewAI, AutoGen, DSPy, or custom - Strong Python; comfortable with async, observability, testing - Hands-on with at least one major LLM provider (Azure OpenAI, Anthropic, Bedrock, Vertex) - Eval-driven LLM development — golden sets, LLM-as-judge, regression gates, multi-step replay - HITL gate / agent governance — has shipped agents with explicit gates, not autonomous-by-default - Prompt injection / data leakage / PII handling — designs and tests defences Requirements - Build agents on the platform's agent runtime — prompt design, tool definitions, multi-step workflows, error handling - Ship agents with eval harness, human-in-the-loop gate config, observability instrumentation, cost meter, and runbook - Co-design agent specs with Tech Lead Applications and Suite Product Owners - Partner with ML Engineers on classical ML model integration into agents - Author golden sets per agent — domain-specific test cases capturing must-pass behaviours - Build regression gates in CI so no agent ships without eval-pass - Implement multi-step conversation replay for agents with stateful interactions - Use LLM-as-judge patterns where appropriate; instrument human feedback collection - Configure HITL gates per agent and per agent plan - Implement gate-progression evidence collection (Shadow data, accuracy metrics, override frequency) - Own per-agent cost meter — tokens, vector queries, model inference; report monthly - Tune model routing and implement caching strategies where appropriate - Consume the enterprise LLM Gateway via standard SDK - Partner with platform AI engineering on embedding model selection and retrieval relevance tuning - Mentor seed-programme engineers and contribute to the agent-engineering playbook Preferred Qualifications - Open-source contributions to agent frameworks (LangChain / LangGraph / DSPy) - Multi-agent system at scale in production; retail / commerce / fintech agentic workflows (supplier onboarding, contract intelligence, comparable) - Causal inference exposure (DoWhy / EconML) - Thai-language NLP (PyThaiNLP, WangchanBERTa, SEA-LION, Typhoon) - Vendor certifications such as Databricks Generative AI Engineer or Azure AI Engineer Associate

Related Job Pages

More Artificial Intelligence Jobs

A-Players logo

Talent Engineer – AI Automation

A-Players

Building top-performing teams for the best product companies in Ukraine and the US

Part TimeRemoteTeam 11-50H1B No Sponsor

• Help define Talent Engineering in Ukraine: build AI agents, workflows, and analytics that transform how high-bar recruiting gets done • Build the AI systems that make our Talent Partners unstoppable • You'll know this role is working when: Time-to-first-candidate drops from ~2 weeks to 2-3 days • When a search opens, the first qualified candidate hits the client within days, not weeks • Talent Partners run ~10 high-signal interviews per role, up from ~5, because you've taken manual sourcing off their plate • 3-4 sourcing hypotheses run in parallel from week one - no more sequential testing • Team Tailor becomes the single source of truth • You'll prototype, benchmark, and ship weekly, and document what works and what doesn't • Expect to shadow live searches for the first 2-3 weeks before making any changes

Europe
Valtech logo

AI Adoption Lead

Valtech

The experience innovation company.

Full TimeRemoteTeam 5,001-10,000Since 1997H1B Sponsor

• Own and evolve the enterprise activation AI strategy, with accountability for AI eco-system governance, platform, tool, and model activation, and end-to-end value optimization • Assess, shape the existing AI vendor, and platform landscape to identify value optimization opportunities aligned to business priorities, enterprise constraints, and security requirements • Define pragmatic governance, operating models, and guardrails that enable responsible AI adoption without creating unnecessary friction • Establish frameworks to measure usage, risk, and optimization opportunities across our enterprise landscape and our workforce • Monitor emerging AI technologies, market developments, and vendor roadmaps to inform strategic decisions and maintain competitive advantage • Partner with business leaders to enable decisioning and to connect this to enterprise IT execution • Act as a trusted advisor rather than a reactive order taker • Work within, and orchestrate across, IT and cybersecurity teams to reduce unnecessary friction while working within a risk tolerant framework appropriate to address the business needs • Design and promote pragmatic AI governance models that drive low process friction and high AI adoption • Balance speed, innovation, and security in decision-making • Drive cultural change within IT toward a consultative, business-enabling mindset • Challenge legacy control-driven behaviors that limit innovation • Influence stakeholders across multiple levels without relying solely on authority • Educate business and IT teams on AI opportunities, risks, and mitigation strategies

North Macedonia
Valtech logo

AI Adoption Lead

Valtech

The experience innovation company.

Full TimeRemoteTeam 5,001-10,000Since 1997H1B Sponsor

• Own and evolve the enterprise activation AI strategy, with accountability for AI eco-system governance, platform, tool, and model activation, and end-to-end value optimization • Assess, shape the existing AI vendor, and platform landscape to identify value optimization opportunities aligned to business priorities, enterprise constraints, and security requirements • Define pragmatic governance, operating models, and guardrails that enable responsible AI adoption without creating unnecessary friction • Establish frameworks to measure usage, risk, and optimization opportunities across our enterprise landscape and our workforce • Monitor emerging AI technologies, market developments, and vendor roadmaps to inform strategic decisions and maintain competitive advantage • Partner with business leaders to enable decisioning and to connect this to enterprise IT execution • Act as a trusted advisor rather than a reactive order taker • Work within, and orchestrate across, IT and cybersecurity teams to reduce unnecessary friction while working within a risk tolerant framework appropriate to address the business needs • Design and promote pragmatic AI governance models that drive low process friction and high AI adoption • Drive cultural change within IT toward a consultative, business-enabling mindset • Challenge legacy control-driven behaviors that limit innovation • Influence stakeholders across multiple levels without relying solely on authority • Educate business and IT teams on AI opportunities, risks, and mitigation strategies

Bulgaria
Mindrift logo

Contracts Attorney - Freelance AI Trainer

Mindrift

Apply → Pass qualification(s) → Join a project → Complete tasks → Get paid. Project time expectations: Tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements; This is an estimate, not a guaranteed workload, and applies only while the project is active. Note: Rates vary based on expertise, skills assessment, location, project needs, and other factors. Higher rates may be offered to highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are shared per project.

Role Description Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project-based, not permanent employment. What this opportunity involves: - Generate prompts that challenge AI; - Evaluate AI-generated solutions for correctness, assumptions, and logic; - Improve AI reasoning to align with first principles and accepted standards; - Apply structured scoring criteria to assess multi-step problem solving. Qualifications - Degree in law (Bachelor, J.D., LLM, FLLM) within the US context - 2+ years of legal practice experience within US jurisdiction - Strong written English (C1/C2) - Stable internet connection Requirements This opportunity is a good fit for legal consultants, attorneys with experience in US law open to part-time, non-permanent projects. Benefits - Earn up to $75 per hour equivalent, depending on level and pace of contribution. - Compensation varies across projects depending on scope, complexity, and required expertise. - Other projects on the platform may offer different earning levels based on their requirements. Company Description Apply → Pass qualification(s) → Join a project → Complete tasks → Get paid Project time expectations: - Tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements. - This is an estimate, not a guaranteed workload, and applies only while the project is active.

United States
$75 / hour
Job Closed