Torre.

I helped recruiters find candidates and assess their experience.

+43%Evaluation quality

Quality improvement from the selected model integration after comparing three LLM providers.

−23%Model cost

Lower cost for the selected integration in the model comparison.

01 / Sitemaps & discovery

More candidate profiles appeared in Google.

Useful public profiles were missing from search results, while outdated pages stayed listed. I rebuilt the sitemaps and refreshed listings when profiles, companies, or hiring status changed.

+1,700%Google-indexed pages
torre / engineering in contextIllustrative sample · No employer data
Career profile01

Alex Okafor

Software engineer

Node.jsBackend APIs
Page visibility
SEARCH DISCOVERY

Public profiles.
Current sitemaps.

sitemap.xmlUpdated
01/maya-chenPublic
02/alex-okaforIncluded
03/jordan-reedPublic

Useful URLs for search engines.
A sitemap helps discovery; it does not guarantee indexing.

PUBLIC PAGEIn the sitemap.Visibility changes. The directory follows.

Profile, company, and careers pages use separate inclusion rules. A content change refreshes the relevant listing.

How I built itRead the engineering details

A longer sitemap could still send a search engine to empty or outdated pages. I focused on useful coverage and kept existing listings current through events and cache invalidation. An update needed to change the relevant listing without rebuilding every directory.

Scala & SQL
Build the sitemap endpoints and select the records each directory needs.
Events & RabbitMQ
Refresh affected listings when content or hiring activity changes.
XML sitemaps & cache invalidation
Serve searchable directories without continuing to return stale versions.

+1,700% Google-indexed pages. Growth in indexed candidate and company pages after the sitemap improvements.

02 / Profile optimization

Relevant experience became easier to spot.

General profiles made relevant experience easy to miss. I built profile introductions and résumé views tailored to an opening, with checks that kept qualifications faithful to the candidate’s original experience.

+22%Candidate shortlists
−20%Candidate rejections
torre / engineering in contextIllustrative sample · No employer data
ROLE-SPECIFIC PRESENTATION

Relevant experience.
Original facts.

Original experienceSource

Alex Okafor

Software engineer

✓ Original career history retained
Tailored introductionFor this opening
PLATFORM ENGINEER

I build backend APIs01 and background jobs02 for inventory and product data.

01
Connected to the sourceInventory and invoicing APIs · Node.js
Facts stay fixed.Titles. Figures. Supporting experience.

Select an experience to see its supporting claim. The relevant work comes forward; qualifications are not invented.

How I built itRead the engineering details

The model could borrow a skill from the job description that the candidate had never claimed. Checks had to preserve titles, figures, and supporting experience. There was also a waiting problem: I used priority queues and concurrency control so a profile being opened could take the next available generation slot.

Scala & structured LLM output
Turn model responses into fields the application can check and display.
Grounding & validation
Compare generated claims with the person’s existing experience.
Priority queues & concurrency control
Give opened profiles precedence over waiting background work while controlling simultaneous generation.

+22% Candidate shortlists. Increase in recruiter shortlists in profile-optimization experiments.

−20% Candidate rejections. Reduction observed in the profile-optimization experiments.

03 / LLM evaluation

Better AI answers. Lower model cost.

A production model was retiring, and its proposed replacement threatened a threefold cost increase. I compared three providers, checked answers against the candidate’s actual experience, revised prompts, and shipped the best-performing integration.

+43%Evaluation quality
−23%Model cost
torre / engineering in contextIllustrative sample · No employer data
ONE SOURCE. THREE PROVIDERS.

Compare answers.
Check the evidence.

SOURCE EXPERIENCE

Built inventory & invoicing APIs with Node.js.

The opening asks for Kubernetes.
CHECK AGAINST THE SOURCE
Preserved the source evidence

Relevant work and the original technology are retained.

Inspect failures.
Revise the prompt. Test again.

Answers are illustrative, not employer outputs. Cross-model judging supports the comparison; source checks still determine whether a claim is justified.

How I built itRead the engineering details

The evaluations exposed a tension between preventing invention and preserving useful source material. A stricter instruction could remove content it should have kept. Cross-model judging provided another perspective, but I still checked the evidence and used deterministic validation for rules with a definite answer.

LLM evaluation & test design
Turn a vague quality question into repeatable comparisons.
Cross-model judging & validation
Combine evidence-based review with checks for clear rules.
Prompt engineering
Use observed failure patterns to improve the next version.

+43% Evaluation quality. Quality improvement from the selected model integration after comparing three LLM providers.

−23% Model cost. Lower cost for the selected integration in the model comparison.

04 / Match & Rank

Recruiters could see why a candidate matched.

A match score didn’t explain which experience supported it. I connected job requirements to supporting career experience and made the reasons inspectable. Missing evidence stayed distinct from a mismatch.

torre / engineering in contextIllustrative sample · No employer data
EXPLAINABLE MATCHING

Job requirement.
Supporting experience.

THE OPENING

Platform
engineer

Build reliable services.
Work across product and data.

REQUIREMENT IN VIEWBuild backend services
CANDIDATEAO

Alex
Okafor

Software engineer

01Inventory APIs02Background jobs
Original experience
Match

Backend development

Built inventory APIs and background jobs to synchronize product records.

SOURCEExperience 01 + 02

Relevant work supports the requirement. Each factor preserves the distinction between a match, a mismatch, and an unanswered question.

How I built itRead the engineering details

A simpler display would have been misleading if it flattened every factor into yes or no. The work preserved match, mismatch, and unknown states, then let people inspect the evidence without making them read everything at once.

Vue, TypeScript & shared components
Bring explanations into product views without duplicating their behavior.
API contracts & data consistency
Keep the meaning of candidate information aligned across services and screens.
Evidence attribution
Connect a skill or claim to the experience that supports it.
05 / Tracing & product measurement

Engineers could trace failed AI calls.

Failed model calls and poor search results were difficult to investigate. I recorded model attempts and failures, clarified product metrics, and sent the search context and displayed candidates to the team’s review workflow.

torre / engineering in contextIllustrative sample · No employer data
TRACING & QUALITY REVIEW

The successful result.
The failed attempt.

request / sample-1042Result returned
STARTATTEMPTSEND

Both attempts stay visible.
A successful fallback does not erase a failure.

ATTEMPT 01

The failed attempt

The provider failure remains in the trace, even when a later attempt succeeds.

Provider error retained
AO
SEARCH QUALITY REVIEWAlex + the search actually shown.Candidate · requirements · search context
Ready to investigate

Model tracing exposes failed calls. Search context is sent separately to the team’s review workflow, without blocking the recruiter’s search.

How I built itRead the engineering details

The review team needed the result the user actually saw. I worked on carrying that context into the review handoff while keeping a delivery failure from interrupting search. For metrics, I checked what each count represented and kept incomplete periods from distorting comparisons.

OpenTelemetry & Langfuse
Record the parts of model operations, their timing, and failures.
SQL & event measurement
Count a defined population and compare matching time periods.
n8n integration & HTTP
Send useful search context into the review team’s workflow without owning or recreating their receiver.
06 / Product reliability

Interrupted applications could continue without losing progress.

Search, résumé imports, uploads, and messaging could fail partway through an application. I traced the failures across the browser and backend, then repaired recovery and data handling while preserving completed work.

torre / engineering in contextIllustrative sample · No employer data
PRODUCT RELIABILITY

Retry the failed step.
Keep completed work.

Application workspaceAlex Okafor
✓ Résumé imported✓ Profile saved03 Search
Alex_CV.pdfImported successfullyCareer information retained
SAVED PROFILE

Alex Okafor

Backend APIs.
Background processing.

Inventory APIsProduct-data jobs
Completed work stays available.
SEARCH STATUS

Search interrupted

The search paused. Imported information and the saved profile remain available.

✓Work retained.Retry the part that failed.

This example illustrates recovery that preserves progress. Import, upload, messaging, and service-resource failures each needed a correction at the place that owned the problem.

How I built itRead the engineering details

A retry is useful when a dependency fails temporarily; it cannot repair an incorrect data merge or a client created too often. The investigation mattered because each symptom needed a different correction, with existing user progress preserved where possible.

Debugging & resource lifecycle
Find the owner of a failure and correct it without introducing unnecessary machinery.
Asynchronous recovery
Handle interrupted work while preserving completed progress.
Browser APIs & integration
Keep uploads, recordings, and messaging compatible with the surrounding product.
FROM SOMEONE I WORKED WITH

“Not just using AI but keeping a critical mindset in order to get the best out of it.”

Gus GarcíaProduct Engineer at Torre.ai · Direct manager
MY CONTRIBUTION AT TORRE

At Torre, my work crossed backend services, AI evaluation, and the screens people used to make hiring decisions. Following a change through those layers helped me catch problems that were easy to miss in isolation.

Back to selected workExplore NaistroDiscuss an opportunity
Illustrations use explanatory examples, not company screens or private data. Reported impact figures come from my résumé.