We seek an expert 'Query prompt engineer/developer' to help create 4 queries to OpenAI GPT via an API, to produce results similar to ChatGPT. Each query will have a set of do's and don'ts expectations.This is NOT ChatGPT or Chat Completion.

A query to OpenAI via API should get a similar result to chatGPT if the data, model, temperature, token size and expectations are exactly the same.

The CEO is very knowledgeable about what a query to OpenAI via an API is and isn't able to do.

There will be very little compromise on the quality of results expected.
(There is always a way!)

This test project assesses the candidates' capabilities and attitudes. We can discuss lots of long-term work for the right candidate based on their talent, availability and interest.

We already have a technical solution integrating the CEOs local machine, Google Drive, various vectorDBs (which wont always be used), OpenAI and LangChain.

** Scope, Requirements and Expectations *
1] Help the CEO teach and create and write 4 specific queries to OpenAI GPT via an API, that is extremely similar to the desired results (produced via chatGPT)
2] Proactively work to figure out why something is working/not working
3] Work with our amazing developer to tweak/refine our current code and teach if necessary.
4] Record short video walkthrough of how code works

* Deadline *
One successful command prompt query per day. Must meet the desired results or CEO's expectations.
GUARANTEED BONUS ! (this is stackable!):Each additional successful prompt completed in the day = 5%

Mandatory Expectations
You MUST
1 ] have done this type of work before.
2 ] join video calls with screen sharing to collaborate and succeed together
3 ] be happy to make video recorded tutorial. A quick and simple way to explain your code, contribute solutions and suggestions by screen recording (skype, zoom, google meet all do this)
4 ] meet agreed timelines
5 ] be responsive and communicative. We always listen to our people and help work through mistakes - but you must be open, honest and respectful.
6] Work as a team, sharing screens and video calls, to reach common goals.
7 ] create a simpler version of solutions (e.g. query 1+ sample files on your local machine to OpenAI) on your side to test command prompts and do your homework proactively


* Out of Scope *
1 ] Any development work (aside from what is mentioned above)
2 ] ChatGPT command prompts

Acceptance Criteria
1 ] Solution must be optimised for time and token cost efficiency (e.g. we cannot use GPT4 unless critical, run several iterations of queries unnecessarily to run a single command. Although sometimes it is possible)
2 ] Help our main developer integrate any code developments into his application
3 ] Provide a short video walkthrough of the code, queries on how it works or can be adjusted if needed
4 ] Solutions MUST be able to do ALL the specific things discussed, agreed and shown possible.



What we can offer you
--------------------------
1. Opportunities to work with famous external clients (e.g. Disney, Ernst & Young, Credit Suisse)
You can pick contracts that work for you without politics, stress or drama. We manage all of that for you.

2. Multiple internal project opportunities
Become our long-term preferred supplier. We offer you projects that match your skill set and interest.

3. Great working environment
Be welcomed into our happy, supportive and helpful family environment (read our Upwork reviews).

4. Bonuses!
We value great people.

We reward people on trust, loyalty, quality of work and proactiveness financially through more contracts, client opportunities, and/or more exclusive opportunities to partner with us.

How we reward
--------------------

We operate on a fair basis. This is a fixed-price contract with fixed costs, requirements and acceptance criteria. Payment is only made for the full delivery of the project.

We will do everything to help our people become the best and reward the best people to keep them happy.
We reward people based on 4 levels of performance:

STAR SUPPLIER
IF YOU: Deliver work on time, meet acceptance criteria & meet basic company expectations [e.g. attend a few calls, help others, be dependable & proactive]
WE REWARD: 5* Rating + Agreed full contract rate paid + Guaranteed bonus + Long-term partnership + recommendation to global clients + invitations to work with us on big fortune 500 clients (you will be protected from politics by us)

GOOD SUPPLIER
IF YOU: Deliver your work as promised on time, meet acceptance criteria
WE REWARD: 5* Rating + Agreed full contract rate paid

ONE-OFF SUPPLIER
IF YOU: Deliver your work as promised, meet acceptance criteria (but work is late)
WE REWARD: Agreed full contract rate paid only

POOR SUPPLIER
IF YOU: Don't meet acceptance criteria or become unresponsive, unreliable or difficult.
WE REWARD: Lower rating and,or payment to be negotiated.

What is the most complex command prompt that you've successfully created to OpenAI via an API? Explain what it did and why it was complicated.
Write a API completion prompt to minimise a paragraph using abbreviations (e.g. min. instead of minimum) & symbols (e.g. & instead of and) without losing key details (e.g. dates, values, metrics). Choose any sample text & show your results.
Do you have any questions about any of the following: 1) Paid trail project, 2) Payment per successful command prompt (4 milestones), 3) 5% Stackable bonus. We expect 1 prompt successful/day. If you do 2 more = 10% bonus, 4) Our reward scheme
What is your availability between 9am -5pm UK time on the weekdays? This is a flexible job, but we must agree and commit to some times to ensure calls with the CEO or developer are possible.
Do you have any questions or challenges with the job description, expectations, deadlines, or acceptance criteria?

Type of work: Remote/ Freelance

Target Rate: $226-250

Language: English

Experience Level: With Experience

How to apply:

Send your resume/CV and cover letter to [email protected]

Only candidates fulfilling due requirements will be contacted by e-mail.

Afati i fundit i aplikimit: 08/09/2023 15:31