Senior AI Engineer

PT. Gemilang Satria Perkasa opens job vacancies for the following positions:

Senior AI Engineer

PT Gemilang Satria Perkasa is looking for a Senior AI Engineer to lead, architect, and deliver production-grade AI agent systems, LLM applications, RAG pipelines, and intelligent automation solutions for enterprise, defence, security, and digital transformation projects.

Responsibilities

• Architect and build production-grade AI agents using LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, or similar frameworks.

• Develop RAG pipelines using embeddings, vector databases, hybrid search, and document ingestion.

• Integrate and evaluate LLMs such as OpenAI, Claude, Gemini, LLaMA, Mistral, or other models; drive model selection decisions based on performance and cost trade-offs.

• Build backend APIs using Python, FastAPI, Flask, or equivalent tools.

• Connect AI agents to APIs, databases, documents, dashboards, and enterprise systems.

• Design advanced prompt engineering strategies, memory management, tool calling, structured output, and multi-agent workflow orchestration.

• Define evaluation frameworks, reduce hallucinations, and continuously improve system reliability and accuracy at scale.

• Deploy and maintain AI services using Docker, Kubernetes, Git, Linux, CI/CD pipelines, and production-ready engineering practices.

• Lead technical design and architecture reviews for AI systems; set coding standards and best practices for the team.

• Mentor and coach junior and mid-level AI Engineers; conduct code reviews and technical onboarding.

• Collaborate with product, business, and stakeholder teams to translate requirements into scalable AI solutions.

Requirements

• Bachelor’s degree in Computer Science, AI, Data Science, Software Engineering, or a related field (Master’s degree is an advantage).

• 5+ years of experience in AI Engineering, ML Engineering, Backend Engineering, or Software Engineering, with at least 2 years in a senior or tech lead capacity.

• Proven track record of designing and delivering LLM, RAG, agentic AI, and AI automation systems in production environments.

• Expert-level Python programming skills; proficiency in TypeScript or another secondary language is a plus.

• Experience with LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, or similar.

• Experience with vector databases such as FAISS, ChromaDB, Qdrant, Milvus, Weaviate, Pinecone, or Elasticsearch.

• Proficient with REST API design, SQL/NoSQL databases, Docker, Kubernetes, Git, Linux, and cloud infrastructure basics.

• Deep understanding of prompt engineering, embeddings, retrieval strategies, evaluation pipelines, and LLM limitations in production contexts.

Preferred

• Experience in defence, security, intelligence, OSINT, fintech, compliance, or enterprise automation.

• Experience with local LLM deployment, fine-tuning, Whisper, knowledge graph, or multimodal AI.

• Familiarity with AI governance, cybersecurity, and data privacy.

• Able to independently manage complex, multi-stakeholder AI projects in a fast-paced system integration environment.

• Portfolio or demonstrable experience leading or architecting end-to-end AI solutions in an organizational or enterprise context.