Skip to main content

Bjak

LLM Application Engineer

United States (Remote)fulltimemidAdded 2 days ago

About this role

Build intelligent, production-ready AI agent workflows that power A1's smart assistant for everyday tasks. You'll design agentic systems, integrate LLMs with tools and APIs, develop evaluation frameworks, and own the full stack from model behavior to user experience.

What you'll do

  • Design and ship LLM-powered applications and multi-step agent workflows with reliable orchestration
  • Develop prompting strategies, context engineering, and structured outputs to improve model behavior
  • Build evaluation frameworks and datasets to measure AI quality, reliability, and catch regressions
  • Integrate LLMs with external APIs, databases, vector stores, and internal services for tool-use
  • Debug and optimize AI systems across the full stack—from model outputs and prompts to backend services
  • Establish production practices for observability, experimentation, and continuous improvement of AI systems

What they're looking for

  • Python
  • LLM APIs and model providers (OpenAI-compatible, open-weight models)
  • Agent frameworks and orchestration systems
  • Prompt engineering and context management
  • Vector databases and retrieval systems
  • PyTorch or JAX
  • Distributed systems and backend service design
  • AI evaluation and dataset development
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Bjak

Bjak is a Southeast Asian fintech super app offering insurance, payments, savings, wallets, and investment products through a unified platform. The company is hiring full stack engineers, backend engineers, iOS developers, and Android engineers to build scalable features and reliable systems across mobile and web products.

Website
bjak.com
View all jobs at Bjak

Likely interview questions

  • Walk us through a time you built an LLM-powered application end-to-end—what were the biggest challenges in making it reliable?
  • How have you approached debugging when an LLM produces unexpected outputs in production? What techniques did you use?
Unlock all 7 questions free — and practice them live →