Senior AI Product Engineer

sa.global

. Own the reasoning core of empower, sa.global's industry-specific agentic AI platform .

Posted 9/24/2026full-timeBelgrade • SerbiaSeniorWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in backend software development with a focus on AI-adjacent technologies, including proficiency in Python and experience with agent orchestration frameworks. Capable of designing and implementing production APIs, integrating LLM/AI APIs, and utilizing MLflow for evaluation tracking.

Highest-signal resume keywords

Backend Software DevelopmentPython ProgrammingAgent-Orchestration FrameworksLLM/AI API IntegrationMLflow Experience

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

Production API DesignDistributed ServicesPostgreSQLLangGraphCloud-Native DeploymentContainerizationCI/CDNeo4jDSPyLLM Evaluation Methodology

Soft Skills

AgencySystemic ThinkingStructured CommunicationOwnershipQuality DisciplineComfort with Ambiguity

Tools & Technologies

MLflowClaude CodeCursorCopilotCodexVLLMOllamaLlamaIndexGraphRAGPgvector

Industry Keywords

Agentic AIMulti-Agent WorkflowsHuman-in-the-Loop ControlsEvaluation HarnessesBusiness Knowledge Graph

Tech Stack

Tools & technologies

AirflowAzureCloudNeo4jPostgresPython

About the role

Key responsibilities & impact

Own the reasoning core of empower, sa.global's industry-specific agentic AI platform
Design and implement multi-agent workflows and orchestration graphs using frameworks such as LangGraph
Apply DSPy or comparable declarative prompt-programming approaches
Build and maintain MLflow-tracked evaluation harnesses measuring accuracy, faithfulness/hallucination rate, latency, and instruction-following
Architect agent memory, tool-calling, guardrails, and human-in-the-loop controls for production workflows
Prototype retrieval architectures over the Neo4j-backed Business Knowledge Graph using GraphRAG, LlamaIndex, pgvector, and pg_search
Collaborate with Level I engineers
Decide when agentic patterns are warranted versus simpler deterministic approaches
Use AI coding agents to prototype and stress-test agent architectures, generate evaluation scaffolding, and build custom skills and tooling

Requirements

What you’ll need

5+ years of backend software development experience
Python as the primary language for AI-adjacent work
Proven track record designing and shipping production APIs and distributed services
Hands-on experience integrating LLM/AI APIs, including Anthropic, OpenAI, or open-weight models via vLLM/Ollama
Working knowledge of PostgreSQL with pgvector and pg_search, chunking, and hybrid vector/full-text search
Familiarity with MCP (Model Context Protocol)
Experience with cloud-native deployment, containerization, and CI/CD; Azure preferred
Daily hands-on use of Claude Code or a comparable AI coding agent such as Cursor, Copilot, or Codex
Deep hands-on production experience with LangGraph or a comparable agent-orchestration framework
Working knowledge of LlamaIndex or a comparable RAG framework
Experience using MLflow or a comparable tool for experiment and evaluation tracking
Solid grounding in LLM evaluation methodology
Experience designing agent architectures end-to-end, including planning, memory, tool use, guardrails, and failure recovery
Nice to have: hands-on Neo4j and Cypher experience
Nice to have: Prefect or Airflow experience
Nice to have: DSPy or similar prompt optimization experience
Nice to have: fine-tuning or preference-optimization experience
Nice to have: open-source contributions to agent or LLM orchestration frameworks
Nice to have: experience translating agentic-AI concepts into shipped products
Agency, systemic thinking, structured communication, ownership and quality discipline, and comfort with ambiguity

Benefits

Comp & perks

Remote work option with a hybrid, flexible working model depending on candidate location