Careers
What AI engineering job descriptions actually ask for
We read 57 current AI engineering job posts. Most ask for years of software work, not years of AI. What they really want: evals, failure modes and shipping.
· Prafull B.
Prafull designs the architecture of production AI systems at Qollabra. His work includes a document AI platform for the U.S. legal sector: OCR and extraction over document sets of thousands of pages, source tracing, specialist review and processing pipelines that recover from failure.
He works on complex domains, where the rules are intricate, the data is messy and mistakes are expensive, and writes about the part of AI engineering that demos skip: evaluation, permissions, recovery and cost.
Articles
Careers
What is a forward deployed engineer?
An engineer who sits with the client's team, learns how the work gets done and builds AI into it. Where the role came from, what it asks for, and who it suits.
· Prafull B.
Careers
Why does every tech job description mention AI now?
In tech, one in five job posts or more mentions AI, and nearly half in data roles. Why it happened, how to tell real demand from copy-paste, and what to build.
· Prafull B.
Building in public
Why I'm building QuizzaHut 2, an open-source job-hunt CLI
Job seekers juggle a tracker, a resume, a chat and a sheet. Why the new QuizzaHut is an open-source agentic CLI, and why it won't auto-apply on LinkedIn.
· Prafull B.
Careers
Why AI engineering pays more, and what would change it
Companies pay for people who can make AI work inside a product. Why there are few of them, what the hiring data shows, and what keeps its value.
· Prafull B.
Software delivery
Software development after AI: review is the job now
AI writes the first draft. Code arrives faster and in bigger pieces, and review becomes the bottleneck. What changed on our team, and what I'd change tomorrow.
· Prafull B.
Careers
What gets an AI engineering profile a reply
One real project, explained well, does more than twenty certificates. What a reviewer looks for, and how to answer 'what broke in production?'
· Prafull B.
Evals
Product management for AI features: the test set is the spec
AI features don't fit strict test cases. What worked for us: real examples, good and bad answers, and a pass bar agreed with the client before building.
· Prafull B.
AI engineering
Prompt, context, loop engineering: why the names keep changing
Prompt engineering, then context engineering, now loop engineering. Each name came when the last one hit its limit. One skill stayed the same underneath.
· Prafull B.
AI engineering
What changes when an AI agent gets a million requests
At scale the first limit is the model provider's quota, not your servers. Tokens per minute, shared rate limits, fair queues and cost per request.
· Prafull B.
AI engineering
Security for agentic workflows: put the rules in code
Prompts don't enforce permissions. Where the rules for an AI agent live, the three-part test for injection risk, and why every step must be safe to repeat.
· Prafull B.
AI engineering
Why so many AI agents ship as CLI tools
The terminal already has every tool an agent needs: git, tests, files and every CLI you installed. Why agents ship there, and how to keep shell access safe.
· Prafull B.
AI engineering
Server-side vs client-side agents: where should yours run?
Where an AI agent runs decides whose keys it holds, whose data it sees and who pays for the tokens. Backend code vs frontend code, with the same trust rules.
· Prafull B.
AI engineering
Why production agents are rare, and what has to exist first
Most AI agents in demos are workflows, and that is fine. What keeps real agents out of production is the code around the model: permissions, logs, limits, undo.
· Prafull B.
Community
The QuizzaHut story: 3,000 members in 3 days, no ads
A Telegram bot we built for our CDAC exams, what it taught me about building for a community, and why I'm building it again for the job hunt.
· Prafull B.
AI engineering
Why AI features need background jobs
One click became 10-15 model calls and requests ran for minutes. What moved to a worker, what broke when it crashed, and the small version to build first.
· Prafull B.
AI engineering
Why your chat feature needs SSE, and when to use WebSockets
A slow AI answer behind a spinner looks broken. How SSE fixes it, when WebSockets fit better, what proxies do to streams, and why long work belongs in a job.
· Prafull B.
AI engineering
What you build around an LLM API call in your backend
One endpoint, one model call is a demo. A production feature needs a schema, domain checks, timeouts, a log of every call and a way to say I don't know.
· Prafull B.
AI engineering
What is AI engineering? Lessons from a chatbot that fell flat
AI engineering starts with an API call. The work is finding where a probabilistic feature fails on real data, and defining requirements that let you check it.
· Prafull B.