Senior AI Engineer

📋 Description

• • Architect and ship production-grade, end-to-end LLM systems that power Nessolabs’ next-generation products. You will own the full lifecycle—from prompt engineering and retrieval-augmented generation (RAG) pipelines to agent orchestration—using the OpenAI SDK and LangChain LangGraph, ensuring our customers experience lightning-fast, context-aware AI interactions.
• • Build rock-solid Python backend services and RESTful APIs with Pydantic for type safety and automatic validation. Your code will serve as the backbone for data ingestion, model inference, and downstream analytics, all while maintaining >99.9 % uptime and sub-second latency.
• • Design and implement scalable search and retrieval solutions on top of OpenSearch / Elasticsearch. You will tune vector indexes, hybrid sparse-dense scoring, and real-time re-ranking to deliver highly relevant results across millions of multilingual documents.
• • Orchestrate asynchronous and scheduled workloads using Celery or Prefect. From nightly model retraining to on-demand batch inference, your pipelines will be fault-tolerant, observable, and cost-efficient, running seamlessly across cloud regions in Indonesia and beyond.
• • Model, migrate, and query data with SQLAlchemy, ensuring ACID compliance and elegant schema evolution. You will optimize complex joins, craft performant ORM patterns, and maintain data lineage for downstream ML features.
• • Add enterprise-grade observability with OpenTelemetry—distributed tracing, metrics, and structured logs—so every request, vector search, and LLM call is transparent and debuggable in production.
• • Collaborate daily with product managers, designers, and fellow engineers in a fully remote, async-first culture. You will run lightweight RFCs, conduct blameless post-mortems, and ship iterative improvements every sprint.
• • Stay on the cutting edge of AI research. You will prototype emerging techniques (e.g., multi-modal embeddings, chain-of-thought distillation, guardrail frameworks) and champion their adoption through internal tech talks and documentation.
• • Mentor junior engineers and contribute to our internal AI guild. Your code reviews and design docs will raise the bar for quality, security, and ethical AI practices across the organization.
• • Influence the product roadmap by translating customer pain points into technical solutions. Whether it’s reducing hallucinations, adding Bahasa Indonesia support, or enabling on-device inference, your voice will shape what we build next.