Open Position

Junior Software Engineer

  • Dhaka, Bangladesh
  • Full-Time
  • On-site
  • 0-2 Years
Apply Now

Nagorik Technologies is an AI-native enterprise technology company with 200+ in-house engineers building software, AI systems, cloud platforms and secure infrastructure for complex, business-critical operations. We have built, run, licensed and white-labeled our own products, so we own what happens after launch: reliability, security, scale and maintainability. Our work spans fintech, telecom, SaaS, healthcare, government and retail. We are ISO 9001:2015 and ISO 27001:2022 certified and an AWS Partner.

How we build software now

Our engineers use AI agents across the software lifecycle, from analysis and design to coding, testing and operations. Agents do not replace engineering judgment. They raise the bar for it, because an agent will confidently do exactly what a vague instruction allows. The skills that decide the result are:

  • Context: understanding the business problem, the existing system, the data and the constraints well enough to give an agent what it needs, and to know when its output is wrong
  • Specification: writing clear, testable specs and acceptance criteria that leave nothing to guess
  • Prompting: writing precise, structured instructions, examples and project rules for the task at hand
  • Loop engineering: designing the plan, act, verify and retry cycles an agent runs, including when it must stop and ask a human
  • Harness engineering: building the tools, permissions, sandboxes, tests, evaluations, hooks and CI gates that keep agent work inside safe, measurable limits
  • Verification and ownership: reviewing every change, proving it works, and being accountable in production

We measure engineers on outcomes shipped, defects avoided and systems that stay up, not on lines typed. A Claude certification is an advantage at every level.

The role

You will start your career learning how to work with AI agents properly, which is harder than it looks. An agent produces good work only when the engineer gives it the right context, a precise spec and a clear way to check the result. You will learn to do all three, and to understand every line you approve. You will be paired with a senior engineer who reviews your work and teaches you how production systems behave. You will also see far more real code, and far more real mistakes, than a traditional junior role allows.

What you'll do

  • Learn the business and the codebase behind each task before you start: read the requirements, the existing code, the data model and the related tickets
  • Turn well-scoped tickets into clear task specs and acceptance criteria that leave nothing to guess
  • Write prompts and project instructions using our templates, and see how small changes in context change the result
  • Work inside our agent loops and harness: run them, read where they fail and report why (missing context, vague spec, weak tests)
  • Write unit and integration tests, and use them to check generated code before it merges
  • Read, explain and question every change: why this query, why this structure, what could break
  • Fix bugs, trace issues through logs, and learn how our APIs, databases and queues fit together
  • Follow our security, review and release practices, and flag anything that looks unsafe
  • Document what you build and what you learned

What you bring

  • Bachelor's degree in CSE, EEE, IT or a related field, or equivalent proven skill
  • 0 to 2 years of experience; strong fresh graduates and career changers with real projects are welcome
  • Solid grasp of the basics: OOP, data structures, SQL and relational databases, REST APIs
  • Working knowledge of at least one of PHP (Laravel), JavaScript/TypeScript (Node.js, NestJS, Next.js) or Python
  • Comfort with Git and pull request workflows
  • The ability to read code you did not write and explain what it does
  • Clear, structured writing: you can state a problem and its acceptance criteria in a few sentences
  • Curiosity and honesty: you ask when you do not understand, and you say so when generated code looks wrong

Advantages

  • A Claude certification or completed Claude coursework
  • Hands-on use of AI coding assistants on a personal, academic or open-source project, and a view on why they succeeded or failed
  • A project you built and deployed, even a small one
  • Basic Docker, Linux and cloud familiarity

What you will grow into

Within 12 to 18 months, you own small features end to end, write specs and prompts that produce reliable results, and review other people's pull requests with confidence. The path leads to Software Engineer.

What you get

  • Competitive salary based on skill and potential: [BDT range to be confirmed]
  • Two days weekly leave
  • Two festival bonuses
  • Yearly performance-based increment
  • Health insurance and wellness programs
  • Complimentary breakfast, lunch and evening snacks
  • Flexible working hours
  • A named mentor, structured onboarding and paid time to learn

How we hire

Short screening call, a practical task where you may use AI tools and must show your spec, your tests and your reasoning, then a conversation with the team. We care more about how you think and verify than what you memorized.

Apply Now