Computer: what will software developers do in 2027?

• Marc Benioff, billionaire chief of the $315 billion business software giant Salesforce, is set to lay off 1,000 people and said that in 2025 he would not hire any new engineers.
• Google, quietly asked 20,000 workers in its Android and Pixel operations — a tenth of its global workforce — to “voluntarily exit” amid the AI boom.
• Mark Zuckerberg, has laid out plans to cut 5 per cent of Meta’s 72,000-strong workforce, just weeks after warning that 2025 will be the year that AI engineering “agents” will rival mid-level human coders. Zuckerberg said: “This is going to be a profound milestone and potentially one of the most important innovations in history.”

In my work i have the pleasure of collaborating with a lot of younger software developers / engineers in multiple countries and continents. What I'm seeing is that a large majority of them don't see that the light in the tunnel is actually the train, and this concerns me a lot.

To be sure, I also see a lot of older, much more experienced professionals, also not getting the tectonic shifts happening under our feet but at least they have some track record and experience and will have a better chance of surviving, maybe, hopefully..

But what I hate to see is smart young individuals going through college and university education today with a lack of understanding of the future waiting for them. This is a tragedy in the making and I personally hold the education system responsible for also not getting what is happening. I as an educator myself am doing all I can do to add AI knowledge and practical experience into my own classes but this is not enough, and I don't know how the universities will respond to what is clearly happening in the business world and the "job market".

So I asked my computer (today called ChatGPT, Claude, etc..): what will software developers do in 2027?

This is only 2 years from now not 20, 10 even 5 years. just a mere two years from today! The range of skills and capabilities is nowhere near what is being taught in the traditional software curriculum today, and the expectation is when the students graduate in 2 or 3 years they will be able to get jobs with what they were taught. Hopefully a fast re-alignment will take place later this year and in 2026 to divert this Titanic from the iceberg.

I don't want to sound too dramatic and sensational and cause fear, but really there is valid reason to be fearful if we don't adjust.

Let's get into the conversation:

Answer: By 2027, the role of software developers will likely evolve significantly due to advancements in AI, automation, and new computing paradigms. Here’s what software developers will likely be focusing on:

1. AI-Augmented Development

• AI coding assistants (like GitHub Copilot, GPT-based agents, and future iterations) will take on even more of the repetitive coding tasks.
• Developers will focus more on designing and orchestrating AI systems rather than writing boilerplate code.
• Prompt engineering and fine-tuning AI models will be a core skill.

2. More Abstraction, Less Boilerplate

• Low-code/no-code platforms will reduce the need for manually writing large portions of code, allowing developers to focus on higher-level architecture.
• Backend development may shift toward API composition and orchestration, as AI tools handle much of the logic generation.

3. Human-in-the-Loop AI Systems

• AI will generate code, but developers will act as validators, curators, and editors rather than just coders.
• Debugging AI-generated code will be a specialized skill.
• Conversation Engineers (like what you’re defining at Visional) will become a formalized discipline.

4. Increased Focus on Systems Thinking

• Rather than coding individual features, developers will need to think about how distributed systems, AI models, and real-time applications interact.
• Edge computing and decentralized architectures (e.g., Web3, federated learning) may grow in relevance.

5. AI Agents as Software Engineers

• AI-powered agents may design, test, and deploy software with minimal human intervention.
• Developers may shift towards managing AI agents instead of writing every line of code themselves.
• Expect collaboration between AI-driven automation and human oversight.

6. Specialization in AI, Cybersecurity & Ethics

• AI safety, cybersecurity, and ethics will become even bigger concerns.
• Developers may spend more time ensuring AI systems are trustworthy, explainable, and bias-free.
• Regulatory compliance will be a growing area of expertise.

7. Embedded AI in Everything

• AI will be deeply integrated into consumer and enterprise software.
• Developers will need to optimize AI models for real-time inference, personalization, and privacy-first computation.
• On-device AI will become common for edge computing and offline applications.

8. New Interfaces & Modalities

• Voice, AR/VR, and multimodal interfaces will be more common.
• AI-powered development will focus on creating dynamic, context-aware interactions.
• Personal AI agents will require developers to design more natural, contextual conversations.

9. Developer Experience (DX) as a Priority

• With AI-assisted coding, the challenge shifts to creating great developer experiences—simplified APIs, better documentation, and intuitive developer workflows.
• Tooling and infrastructure (e.g., LLMOps, AI observability) will become major areas of focus.

10. Software Engineering Becomes More Strategic

• Developers will spend less time on repetitive coding and more on solving business problems through software.
• The role will shift from "writing code" to "curating intelligent systems that work together."

By 2027, software developers won't just be coding—they'll be architects of AI-driven ecosystems where human oversight, decision-making, and strategic thinking become the most valuable skills.

Where do you see yourself fitting into this shift?

Me: I'm screwed, but let's not divert and talk about me ;)

Okay so what are the job prospects in 2025 for traditional development roles? are developers getting laid off more than before, are job opening increasing or declining, give me some metrics and numbers.

Computer: As of February 2025, the job prospects for traditional software development roles are experiencing notable shifts influenced by industry layoffs, automation, and evolving skill demands.

Current Employment Trends:

• Layoffs: The tech industry has seen significant workforce reductions over the past few years. In 2024, over 150,000 employees were laid off across 542 companies.
• Declining Developer Employment: Between January 2018 and January 2024, the number of employed software developers in the U.S. decreased, with the median base pay for developers growing by 24% during this period, lagging behind the 30% growth for all U.S. workers.

Factors Influencing Job Prospects:

• Automation and AI: The rise of AI-powered coding tools, such as ChatGPT and GitHub Copilot, has automated many routine coding tasks. This shift is leading companies to reassess their workforce needs, potentially reducing demand for roles focused on repetitive coding.
• Economic Adjustments: Economic factors, including cost-cutting measures and market realignments, have prompted companies to streamline operations, often resulting in workforce reductions.

Future Outlook:

• Projected Growth: Despite recent challenges, tech jobs in the U.S. are projected to grow from 6 million in 2024 to 7.1 million by 2034, indicating a positive long-term outlook.
• Evolving Skill Requirements: The demand is shifting towards roles that require advanced skills in AI, machine learning, and cybersecurity. Professionals adept in these areas are likely to find more opportunities as the industry evolves.

In summary, while traditional software development roles face challenges due to automation and economic factors, opportunities remain for those who adapt by acquiring advanced, in-demand skills.

Me thinking: so there seems to be some prediction of tech jobs increasing, but can we trust this prediction? What does "tech jobs" mean? Is a data labeler ad tech job? It can't be all software engineers is my thought.

A good read on what is happening here 'The frog is boiling': is 2025 when AI finally comes for your job?

I'm not asking to throw out the current curriculum, at least not all of it, but some needs to be thrown out, and the rest need to be augmented with informing and training students with AI capabilities and tools. It's like giving our students exoskeletons to super power them.

Of course the professors and educators themselves need the most help right now, and the training is not just "how do i make sure my students didn't use chatgpt to answer the exam questions." This is not even a question any more because in my mind I'd be much happier if my students were good art using AI agents to find answers to questions much faster and then spend time analyzing and pondering the applications. I don't want them clogging their brains remembering data but learning how to ask the right questions and be the conductor of answers into a solution to a problem.

I call on everyone working in the technical education system to pay attention and do something, the cost of not doing major shifts today will be immense not just for our student but also for our own future, the future of the current education system as we know it.

Our company and team is also a key part of our education and it's prudent for organizational leaders to first get it themselves, and then support and guide their teams to become super productive.

Love to hear how some other ideas and thoughts.