Open Position
Principal Software Engineer
Dhaka, Bangladesh
Full-Time
On-site
10+ Years
Nagorik Technologies is an AI-native enterprise technology company with 80+ 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
As Principal Software Engineer, you define how Nagorik engineers software with AI agents. You set the standards for context, specification, prompting, loop engineering and harness engineering across products and teams, and you decide where agents can be trusted and where they cannot. Your aim is speed that never costs us security, reliability or the ability to change our systems later. You work directly with the founders, engineering leadership and enterprise clients, and you are accountable for the technical quality of the company's most critical platforms.
What you'll do
- Define and evolve our engineering lifecycle with agents: how problems are framed, how context is built, how specs are written, how loops run, and how work is verified, secured, released and operated
- Set architecture for large, business-critical platforms across payments, telecom, SaaS and AI products, and guide the teams that build them
- Set the standards for the harness: risk tiers, mandatory human review, permissions and sandboxing, test and evaluation requirements, secrets and data handling, supply-chain and licence controls
- Evaluate coding agents, models and developer tooling on our real codebases rather than vendor claims, and work with our R&D lab to turn results into standards
- Measure what matters: defect rates, review load, cycle time, incident cost and the true cost of agent usage, and use that data to change how we work
- Lead architecture reviews and technical due diligence for major client engagements, and represent engineering in senior client and partner conversations
- Build the next generation of technical leaders through coaching, design reviews and clear written standards, including a path to Claude certification for our engineers
- Take ownership of the hardest problems: cross-system failures, scaling limits, modernization of legacy platforms and security-critical designs
What you bring
- Bachelor's degree in CSE or a related field; a master's degree is a plus
- 10 or more years of professional software engineering experience, including several years as a technical lead, staff engineer, principal or architect for large production systems
- A track record of designing and running high-scale, high-availability platforms, ideally in fintech, payments or telecom
- Deep breadth across backend, cloud, data, security and DevOps, with real depth in at least two
- Substantial hands-on experience directing AI agents on production code, with well-founded opinions on context design, spec writing, loop design and harness design, and on where agents fail
- Experience designing or governing LLM-based systems, including evaluation, guardrails, cost control and data privacy
- Excellent written communication: you can set a standard in a document that a hundred engineers will follow
- Strong commercial judgment and comfort advising senior leaders and clients
- Evidence that engineers who worked with you became better
Advantages
- A Claude certification
- Experience introducing agent-assisted development across a large engineering organization
- Security architecture, compliance (such as ISO 27001) or regulated-industry experience
- Open-source contributions, conference talks or published engineering writing
- Experience with legacy modernization at enterprise scale
What you will shape
This role carries real influence over how an 80+ engineer organization works, which technologies we adopt and which risks we accept. There is room to grow into a CTO-track or head-of-engineering role.
What you get
- Competitive compensation reflecting seniority and impact: [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 direct line to the founders and a clear mandate to change how we build
- Budget for research, tools, certification, conferences and learning
How we hire
Introductory conversation with the founders, a deep architecture discussion on a problem from your own experience, a working session where we present a real agent-governance or system design question and explore it together, references from people who worked under or alongside you, and a final meeting with leadership.