Senior AI Platform Engineer

empower AI Platform - Senior AI Platform Engineer About the Role Anyone can call an LLM API. We're building the harness around it: sa.global Labs is expanding the core team behind empower — our industry-specific agentic AI platform that fuses a domain knowledge graph, a unified data hub, and multi-agent orchestration to automate real enterprise decisions, not demos. We're looking for a Senior AI Platform Engineer to build and operate the scalable foundation underneath it: the APIs, distributed services, data pipelines, and retrieval infrastructure that connect enterprise data, knowledge, and AI capability across the platform.

It's a deliberately opinionated stack — Neo4j for the Business Knowledge Graph, PostgreSQL with pgvector/pg_search for hybrid retrieval, Prefect for pipelines, LangGraph and DSPy powering the agent layer above you — and this is a hands-on senior role: you're building the reliable, secure, production-grade systems that carry real AI workloads for clients across multiple industries, not prototyping in a sandbox.

About empower AI Platform empower is a proactive agentic intelligence layer. It's built around 3 pillars, and this role touches all of them, with a focus on the backend foundation:

Corporate Knowledge (Ontology):

the structured semantic model of a client's domain that gives agents grounded, domain-correct context.

Data Hub:

the layer that unifies, cleans, and serves enterprise data into the platform.

Multi-Agent Skills:

the orchestration layer where reasoning, tool use, and multi-step automation happens.

Platform Stack empower is built on a specific, opinionated stack. Prior hands-on experience with these, not just the general category, is what we're screening for:

Prefect:

orchestration and scheduling data and processing pipelines.

PostgreSQL with pgvector and pg_search extensions : our production vector store and hybrid full text/semantic search layer.

Neo4j:

the graph database underlying the Business Knowledge Graph.

MLflow:

experiment tracking and lifecycle management for models and prompt/agent evaluation runs.

LlamaIndex:

retrieval and RAG pipeline framework.

DSPy:

declarative prompt programming and optimization.

LangGraph:

agent orchestration and control flow.

This role owns the platform foundation – the APIs, data pipelines, services, and infrastructure that everything else runs on – and integrates open-source and commercial AI capabilities into that foundation cleanly and reliably.

Core responsibilities

Design, build, and operate production-grade REST APIs and backend services that power empower's Data Hub and Agent Workflows.

Integrate open-source and commercial AI/LLM tools into backend systems: RAG pipelines, embeddings, vector search, model routing across providers.

Build and maintain the data pipelines and integrations that feed the Business Knowledge Graph.

Own reliability, performance, and security of the services you build, monitoring, cost, and scaling included.

Collaborate with AI Product Engineers to expose the right platform primitives, including tool endpoints, retrieval APIs, and data contracts, for agent workflows to build on.

Required technical experience

5+ years of backend software development;

Python

as the primary language for AI-adjacent work.

Proven track record of designing and shipping

production APIs and distributed services , not just prototypes.

Hands-on

experience integrating LLM/AI APIs

(Anthropic, OpenAI, or open-weight models via vLLM/Ollama) into real applications. This is application integration, not model research.

Working knowledge of retrieval architectures built on PostgreSQL with pgvector and pg_search

(our production stack), chunking, hybrid vector/full-text search.

Familiarity with

MCP (Model Context Protocol)

for exposing tools and data to AI agents.

Comfort with

cloud-native deployment (Azure preferred,

given our Azure DevOps stack; AWS/GCP experience transfers fine), containerization, and CI/CD.

Daily, hands-on use of Claude Code or a comparable AI coding agent (Cursor, Copilot, Codex) as a working method,

scaffolding, refactoring, test generation, and codebase navigation, not just occasional use.

Nice to have

Familiarity with

Neo4j

or other graph databases.

Exposure to

MLFlow

or another experiment-tracking/model-lifecycle tool.

Hands-on experience with Prefect

(or a comparable orchestrator like Airflow) for building and scheduling data and processing pipelines.

Working knowledge of LlamaIndex

(or a comparable RAG framework) for building retrieval pipelines over enterprise data.

Experience with knowledge-graph or

ontology-backed systems.

Prior

exposure to