Ask HN: Freelancer? Seeking freelancer? (June 2023)

---------------------------

Machine learning engineer, specialized in Explainable AI / ML. 13 years professional coding experience, 24 years personal.

Recent highlights:

* Seamless integration of hand-crafted rules with ML-build rules

* Intuitive, visual data/signal explorer: http://explicable.ai

* Implementation in Spark/Scala of treeinterpreter, currently used in production

* Participation to the FICO-Google Explainable Machine Learning Challenge

---------------------------

Tech: SHAP, RuleFit, Random Forest, Word2Vec, PCA, t-SNE, LSH, Scikit-Learn, Spark, Flink, Weka, Databricks, BigQuery, Hive, Postgres, MySQL, Oracle, AWS, Linux, Maven, Git, Java, Scala, Python, CAML, Elm, Javascript, Typescript, React, Spring, Primefaces, d3.js, Three.js

Résumé/CV: https://www.linkedin.com/in/benoitparis/

Github: https://github.com/benoitparis/

Email: benoit.paris.753@gmail.com

Blog: https://benoit.paris

We are a technology company seeking an experienced Software Engineer to work on a contract basis to build software for our company. As a Software Engineer, you will work with our team to design, develop, and maintain software that can be easily scaled and integrated into our existing software architecture. You will also work with consultants who have set a clear scope and requirements for the project. This is a 3-month minimum term contract position with the ability to extend based on deliverables.

Responsibilities: - Design and develop software using modern server-side technologies - Collaborate with our team to understand business requirements and translate them into technical solutions - Ensure that all code is well-written, tested, and maintainable - Write unit tests to ensure that code is of high quality - Build a development environment for the software - Participate in code reviews with consultants and contribute to our development processes - Build APIs and produce clear documentation - Apply knowledge regarding design patterns to software design and development - Work with reporting consultants to present data in a clear and usable way using tools such as Power BI.

Requirements: - 5+ years of experience as a Software Engineer - 3+ years of experience designing and developing microservices - Strong proficiency with server-side technologies (e.g. Node.js, Java, Python) - Experience with databases such as MySQL and PostgreSQL - Experience writing unit tests for code - Ability to build a development environment for software - Docker experience is essential - Ability to work with reporting consultants to present data in a clear and usable way. - Knowledge regarding design patterns for software design and development - Excellent communication and collaboration skills If you are an experienced Software Engineer with at least 5 years of experience and 3+ years of experience designing and developing microservices, with a passion for building scalable software and working with a clear scope and requirements set by experienced consultants, and the ability to work with reporting consultants to present data in a clear and usable way, we want to hear from you.

Please send us your resume and cover letter to apply for this.

Email - directors@booktech.co.uk

Have a nonstandard optimization problem? Could use an interactive visualization to explore complex data? I'd love to hear about it! daniel@andersource.dev

https://andersource.dev

Refine and iterate on gpt agents.

An example project - prove that it's impossible to make a GPT agent that can do the following task:

Please make me a table of all quest diagnostics locations within 10 miles of [zip, city], as well as the yelp review scores for each location. Do it only via browsing, no APIs.

But the constraints:

No API usage (other than google search API), no hard coding of anything to do with quest diagnostics or yelp. Should be a general browser agent. Must have no errors in the result. Must complete the task within 10 minutes.

Inspiration:

* BabyAGI (seems to make progress, but doesn't finish the task within 30+ minutes, and partial progress shows the list of locations isn't quite right. Doesn't succeed with GPT-4 or GPT-3.5)

* Auto-GPT (doesn't succeed with GPT-4 or GPT-3.5 and doesn't seem promising)

* Amoni (fails with an error)

* A human doing it manually (flawless, does the whole thing in a few minutes)

But the steps the human takes to do it manually seem to be things that GPT should be able to figure out.

Your goal would be to prove that it's impossible (and hopefully to make it work in the process!).