Senior AI Engineer - Agentic Platform

Vibehackers; Hinoba-an; On-site; PHP 1,800,000 - 3,000,000; Full time

Benefits offered by this job

Continuous learning

Cross-portfolio opportunities through

Work on cutting-edge AI-driven tech

Job summary

Vibehackers seeks a Senior AI Engineer to design and scale an agentic platform that exposes capabilities as headless MCP-described tools, orchestrating LLM-driven workflows across products. You will drive technical direction, evaluate build-vs-buy decisions, and serve as a reference for Forward Deployed Engineers.

The role requires 6+ years in software engineering with LLM production experience, prompt engineering, and AWS deployment expertise.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, or related field.
• 6+ years of software engineering experience, including 2+ years building production systems with large language models.
• Demonstrated experience setting technical direction and reviewing engineering work.
• Practical experience with prompt engineering, tool/function calling, and agent frameworks (e.g., LangChain, LangGraph).

Responsibilities

• Design headless, MCP-described business logic callable by UIs, AI agents, and automated jobs.
• Build and maintain an LLM orchestration layer to convert model outputs into safe, governed, tool-using actions.
• Implement and extend agent workflows using LangChain/LangGraph and MCP.
• Build and tune RAG pipelines and integrate vector databases for grounding.
• Integrate multiple LLM providers (Claude, OpenAI, Azure OpenAI, AWS Bedrock, Anthropic) via a provider abstraction.
• Develop a Data Agent for governed, read-only access to on-prem/customer data with approval gates and audit trails.
• Support reuse of agent patterns across existing company agents and product pods; partner with Forward Deployed Engineers.
• Deploy agents and inference endpoints on AWS (Lambda, ECS/EKS, SageMaker), integrate with APIs and microservices, and implement evals, cost controls, and observability.
• Collaborate with Data Science, ML Engineering, and MLOps on deployment, monitoring, retraining, and classical ML workloads.

Skills

System Design

Platform Architecture

Orchestration

Prompt Engineering

Agent Frameworks

MLOps

ML Engineering

Deployment & Monitoring

Cost Optimization

Data Governance

API Integration

Technical Leadership

Observability

Production Engineering

Collaboration

Education

Bachelor's degree in Computer Science, Software Engineering, Data Science, or related field

Tools

Docker

Git

CI/CD

Kubernetes

LangChain

LangGraph

AWS SageMaker

Job description

Directly tied to agentic AI and LLM tooling (LangChain/MCP) — builds and integrates AI agents and orchestration, so it aligns closely with vibe coding and AI assistant integration.

About the Role

Build and scale a reusable agentic AI platform that exposes Amtech's capabilities as headless, MCP-described tools and orchestrates LLM-driven workflows across products. Set technical direction, integrate multiple LLM providers, ensure governed access to customer data, and partner with product-embedded engineers to productionize agents.

Job Description

Role

Senior AI Engineer responsible for designing, building, and scaling Amtech's Agentic Platform — a headless, MCP-native intelligence layer that enables reusable agent patterns across multiple product lines. This is a senior, largely self-directed engineering role that sets technical direction, evaluates build-vs-buy decisions, and serves as a technical reference for Forward Deployed Engineers.

Key Responsibilities

• Design headless, MCP-described business logic callable by UIs, AI agents, and automated jobs.
• Build and maintain an LLM orchestration layer to convert model outputs into safe, governed, tool-using actions.
• Implement and extend agent workflows using frameworks such as LangChain/LangGraph and the Model Context Protocol (MCP).
• Build and tune RAG (retrieval-augmented generation) pipelines and integrate vector databases for grounding.
• Integrate multiple LLM providers (Claude, OpenAI, Azure OpenAI, AWS Bedrock, Anthropic) via a provider abstraction to avoid vendor lock-in.
• Develop a Data Agent for governed, read-only access to on-prem/customer data (EnCore and other sources) with approval gates and queryable audit trails.
• Support reuse of agent patterns across existing company agents and product pods; partner with Forward Deployed Engineers to validate and evolve the platform.
• Deploy agents and inference endpoints on AWS (Lambda, ECS/EKS, SageMaker), integrate with APIs and microservices, and implement evals, cost controls, and observability.
• Collaborate with Data Science, ML Engineering, and MLOps functions on deployment, monitoring, retraining, and classical ML workloads.

Requirements

• Bachelor's degree in Computer Science, Software Engineering, Data Science, or related field.
• 6+ years of software engineering experience, including 2+ years building production systems with large language models.
• Demonstrated experience setting technical direction and reviewing engineering work.
• Practical experience with prompt engineering, tool/function calling, and agent frameworks (e.g., LangChain, LangGraph).
• Experience integrating at least one major LLM provider API (OpenAI, Anthropic, Azure OpenAI, or AWS Bedrock).
• Hands-on AWS experience (Lambda, ECS/EKS, S3, IAM, CloudWatch) deploying and operating production workloads.
• Experience with model inferencing (real-time and batch), optimizing latency, throughput, and cost.
• Experience building or consuming RAG pipelines and working with vector databases.
• Working knowledge of ML engineering and MLOps practices (feature stores, model registries, CI/CD for models).
• Familiarity with Docker, Git, and CI/CD practices.

Preferred Qualifications

• Experience with the Model Context Protocol (MCP) or similar agent-tool integration standards.
• Experience building governed, read-only data access layers (audit logging, guardrails, least-privilege access).
• Exposure to Kubernetes and cloud AI/inferencing platforms (AWS Bedrock, SageMaker); AWS certifications are a plus.
• Experience with ERP, MES, or industrial/manufacturing data environments.
• Prior experience embedding with product teams or customer-facing engineering efforts.
• Familiarity with performance monitoring tools (Prometheus, Grafana, Datadog).

Why Join

Work within Vista's ecosystem to shape AI-driven capabilities across enterprise manufacturing software, with opportunities for continuous learning, leadership development, and cross-portfolio collaboration.

Skills

System Design Platform Architecture Orchestration Prompt Engineering Agent Frameworks MLOps ML Engineering Deployment & Monitoring Cost Optimization Data Governance API Integration Technical Leadership Observability Production Engineering Collaboration

Experience Level

Senior

Employment Type

Full Time, Permanent

• Continuous learning
• Cross-portfolio opportunities through Vista
• Work on cutting-edge AI-driven technologies