LLM Application Engineer

Workable locations: Argentina. Colombia. Mexico. Uzbekistan. Georgia, US hours overlap through roughly 5 PM EST when live coordination is neededContractSenior

Salary not disclosed

Apply NowOpens the employer's application page

More jobs in this role

Job Details

Languages: English at C1 or above
Required Skills: PythonGCPPrompt Engineering

Requirements

Have shipped LLM applications in production, including prompts, structured outputs, retries, observability, and failure handling.
Have hands-on experience with Google Gemini, including multimodal text, image, or document workflows and structured extraction.
Have practical experience with at least one other major LLM stack, such as OpenAI or Anthropic.
Have experience extracting structured data from messy inputs such as HTML, PDFs, images, and email-like content.
Have experience with classification or taxonomy systems built on LLM outputs.
Use offline evaluations, regression suites, and production quality metrics with clear acceptance criteria.
Understand token budgeting, model tiers, caching, and batching, and can explain cost tradeoffs.
Have Python backend experience on serverless cloud, such as Cloud Functions, and document stores such as Firestore or similar GCP patterns.
Have English proficiency at C1 or above for client-adjacent debugging with a PM.
Be available for US hours overlap through roughly 5 PM EST when live coordination is needed.
Bring ownership habits, including honest estimates, raising blockers early, and completing releases.

Responsibilities

Own production LLM pipelines end to end, from ingestion and multimodal model calls to structured records and storage.
Design prompt and schema strategies to produce consistent, product-ready results.
Build classification and filtering layers, including taxonomy mapping, audience filters, deduplication, and cleanup logic.
Define and run evaluation harnesses, including golden sets, regression suites, and online metrics.
Track and report against quality targets for completeness, duplicates, incorrect inclusions, image presence, and related product SLAs.
Optimize token usage, model tiering, caching, and batching to manage cost and latency.
Harden long-running asynchronous jobs with timeouts, partial recovery, memory limits, and safe production deployments.
Partner with Flutter/mobile and QA teams on field contracts, review queues, and incident debugging.
Document architecture and runbooks, and recommend model changes, fallbacks, or schema improvements.

View Full Description & ApplyYou'll be redirected to the employer's site