tamersalama

What if the consumers of software are those writing it? Isn't that what usually made software great?

Cenovus Energy Inc. | Senior Software Engineer | Full‑Time | ONSITE | Calgary, Alberta, Canada | Relocation Support | https://cenovus.wd3.myworkdayjobs.com/careers/job/CA-AB-Calg...?

We are hiring experienced Software Engineers to help accelerate delivery of AI solutions at our Energy company. We're looking for full-stack experience, multi-agent workflows, context engineering, agentic development.

Proficiency in Python, Ruby, SQL, JavaScript, frameworks (Rails, Django, Flask/Dash, etc.), AI (OpenAI API, Agno, LangChain, vector stores, RAG pipelines, etc.).

Full ownership of end‑to‑end systems - from problem framing through production - working directly with the team, and our stakeholders across the business on problems that matter.

Reach out through link in bio or apply through the link. No recruiters please.

Would love to hear more (private is OK)

Cenovus Energy Inc. | Senior Software & AI Engineer | Full‑Time | ONSITE | Calgary, Alberta, Canada | Relocation Support

We are hiring experienced Senior Software Engineer and AI Developers to help deliver full‑stack products that bring operational automation and domain intelligence to teams (full-stack, agents, RAG, data pipelines, business dashboards).

You’ll need experience in software engineering, proficiency in Python, Ruby, SQL, JavaScript, full‑stack frameworks (Rails, Flask/Dash, etc.), AI toolkits (OpenAI API, LangChain, LlamaIndex, vector stores, RAG pipelines), and experience with agentic development practices. Canadian work authorization and relocation to Calgary is required.

Reach out through link in bio. No recruiters please.

Are the AI capabilities tapering-off, or commoditized? Building the next Windsurf (iteration 0) doesn't feel it's quite niche anymore.

This goes against the grain - but I’m starting to reimagine enterprise & manufacturing workflows using AI.

Very good leadership support, small (but great) team, huge mandate and uncertainties - and it’s quite exciting.

We are also hiring - AI+Full Stack https://cenovus.wd3.myworkdayjobs.com/en-US/careers/job/Seni...

I love the article & the protocol. However, MCP reminded me (somewhat) of microservices & SOA. Are we creating failure vectors nightmare? Or, is it, because of agents, we can gracefully increase reliability?

How I understood it is that natural language will form relatively large portions of stacks (endpoint descriptions, instructions, prompts, documentations, etc…). In addition to code generated by agents (which would fall under 1.0)

Windsurf feels more organic. Context size will likely still be a problem.

I'm curious about your approach and the nature of those industrial apps. Is it more of recommender agents accessing available sources (through URIs) - or more like explainers. Would be great to connect https://shorturl.at/xdOee

Back in the day, I remember an application that 'analyzed' websites for their Rails hallmarks. I don't know if Rails apps are as distinct nowadays.

Take that RAG parser

I'm currently listening to "Endurance: Shackleton's Incredible Voyage by Alfred Lansing". I've also heard of some of the arguments against Shackleton (I haven't watched the talk).

I have to think of what Shackleton, as a leader (boss), was going through and with uncertainties abound.

28 people who he hired based not only on capability alone, but also for crew (team) fit.

He apparently cared deeply for them, and they in-turn cared for one another.

They managed to work together in the harshest of environments. They all made it.

That in and of itself, is a remarkable feat.

How is this built? What'd be the approach if I'd like to achieve similar results against proprietary data.

References article speak of RAG and RIG - but I wonder if they factor into fine-tuning the models. AFAIK, RAG doesn't play nicely with structured data.

I came to recommend this as well. Still relevant. I hope he's doing well.

The land where “Software Engineers” can’t be named Engineers.

I can't get fine-tune the model ron Apple Silicon due to PyTorch supportability issues. I don't have high-hopes it will be supported.

https://github.com/pytorch/pytorch/issues/77794

https://github.com/pytorch/pytorch/issues/77764

Many World Cup updates do not show up in time (usually delayed by 10-120 minutes). So, Twitter isn't broken but is essentially useless.

I agree that this a big wave, but I'm still struggling to find commercial (read: large organizations) applications.

This is an adaptation into the medical field (generating Medical Images) that might help further train classifiers.

https://bluch.github.io/stablecxr/

Every soccer league is on a different provider. I'm in Canada. The Premier League is on DAZN. MLS is on Apple TV. La Liga is on fuboTV (or Amazon Prime). It's all the same sport. Multiply that by X if another family member is interested another sport. I don't know what the future holds, but the sports entertainment fragmentation might be hurting more than helping. Perhaps Apple is on their way to consolidate.

> I ended up spending more time on tooling setup than actual business logic.

This is exactly why, in 2004, I moved from Java (Struts/Spring/Websphere/XML/...) to Rails. History repeats but we never learn. Kudos to Rails for remaining relevant.

It's the difference between a managed service (getting the 3:00AM phonecall) vs doing it all yourself.

Why is CSS & HTML written in JS?

Coincidentally, four major Canadian producers are uniting in an alliance for net-zero by 2050. The four are responsible for 90% of oil-sands production [1]. To me, this makes Canadian energy a more responsible source compared to many US-based and other international producers. [2]

[1] https://calgary.ctvnews.ca/major-canadian-oilsands-producers...

[2] https://www.nsenergybusiness.com/features/oil-companies-net-...

I’m surprised. With the explosive uptake they needed to keep on differentiating on features. Room searches, tools for moderation, tools for instant feedback, tools for scammer detection, tools for voting, tools for communicating media, and much more. They chose to add a feature that’s absent from competitors but, I’m guessing, nobody had asked for. My gut feeling is that it won’t last.

It provides a platform to the opposition of many dictatorships

> Nobody ever looks at a person driving a ferrari and thinks, "wow, they must have washed a lot of dishes to afford that car," and yet we still think "if I just wash these dishes hard enough I'll drive a ferrari one day."

https://news.ycombinator.com/item?id=25049978

Any studies around 'productivity' has to take into account the time spent on meetings, phonecalls, remote socials, conf calls, etc... and the time for context-switching and directed attention effort. I saw those dramatically increasing during WFH, especially for those teams that were used to co-location.

A different couple