Search by job, company or skills

Everfit

AI Engineer (LLM, Agents)

Save
  • Posted 21 hours ago
  • Be among the first 10 applicants
Early Applicant

Job Description

We're open Junior → Senior - we calibrate on capability and judgment, not years.

Junior candidates should expect to ramp fast on what they haven't seen yet; Senior candidates will own features end-to-end and influence team standards from week one.

Responsibilities

AI Strategy and Roadmap Execution

  • Collaborate with the AI team to understand the company's AI strategy and roadmap.
  • Provide frameworks and conduct research to support the execution of AI projects.
  • Implement best practices for prompt engineering, evals, and continuous improvement of LLM-based features.
  • Identify opportunities for innovation and improvement within Everfit's AI projects.

LLM Workflow and Agentic System Development

  • Design, develop, and deploy LLM workflows, RAG pipelines, and agentic systems across Everfit's AI surface - coaching, programming, voice, vision, and nutrition features.
  • Leverage frontier LLMs from OpenAI and Anthropic, applying them to real product features used by coaches and clients every day.
  • Build evaluation infrastructure - test sets, metrics, LLM-as-judge - to catch regressions before they reach users.
  • Build LLM observability - token cost, latency, failure modes, hallucination signals.
  • Implement guardrails for health-adjacent outputs - refusal logic, tone enforcement, factual grounding.
  • Collect and analyze user feedback to identify and prioritize areas for continuous improvement.
  • Generate reports and dashboards to track key AI quality, cost, and adoption metrics for stakeholders.

Cross-functional Collaboration

  • Work directly with BAs and QAs to define done for non-deterministic AI features, translating AI uncertainty into acceptance criteria QA can verify.
  • Collaborate with product managers, software engineers, designers, and QAs to ensure smooth end-to-end delivery of AI solutions.
  • Support Everfit's initiatives.

Data Infrastructure and Insights

  • Design data pipelines that feed prompts, RAG, and evals from real coach and client behavior.
  • Drive actionable insights and recommendations based on usage data.
  • Contribute to the AI Credits architecture - metering, cost control, graceful degradation.

AI System Maintenance and Improvement

  • Maintain and improve existing AI systems to ensure optimal performance, accuracy, and cost.
  • Run root-cause analyses on production regressions and quality gaps.
  • Enhance the accuracy of health and fitness AI features through continuous eval-driven iteratio

Qualifications

  • Good English communication
  • You've shipped at least one LLM feature to real users - at work or in open-source. Scale doesn't matter; learning from a shipped feature does. Side-project demos that no one used don't count.
  • Proficiency in Python (we use FastAPI as the primary AI codebase).
  • Hands-on experience with LLM workflows, prompts, RAG, embeddings, and structured output - chunking choices, retrieval quality, JSON / function calling, validation, retry on malformed output.
  • Direct experience calling LLM SDKs from OpenAI and/or Anthropic - not only through a framework wrapper. Streaming, tool use, structured output, retries.
  • Familiar with agentic systems - and the bounds an agent loop needs to fail closed (max steps, budget cap, wall-clock cap, defined fallback).
  • Eval-first mindset - you ask how will we measure this before writing the code.
  • Strong understanding of data processing and analysis techniques, particularly in handling health and fitness data.

[Nice to have]

  • Direct experience with our stack - LangGraph, Qdrant, Trustcall, BAML, Langfuse, MCP, n8n.
  • Experience with cloud platforms (AWS, Google Cloud, Azure).
  • Background in health informatics, wearable technology, or personalized fitness programs.
  • Contributions to open-source AI projects or publications in AI research.
  • Experience with the wellness or fitness space.
  • Familiarity with AI coding tools - Claude Code, Cursor, GitHub Copilot.
  • Quantified LLM cost or latency reduction with a number attached.

Our Perks and Benefits

Compensation & Benefits

  • Competitive salary with 13th-month pay and performance bonus.
  • Paid leave — vacation, sick leave, and maternity leave.
  • Full social insurance coverage and premium healthcare benefits.

Build Your Career with Impact

  • Be part of a mission-driven company that's transforming human potential.
  • Empower more than 300,000 coaches across the globe — including Olympic athletes, military trainers, rehab specialists, and celebrity coaches.
  • Make a global impact while building a meaningful, purpose-driven career.
  • Continuous training and mentoring.
  • 1–2 performance reviews annually.

Work Environment

  • English-speaking, international environment promoting open communication and collaboration.
  • Work alongside world-class talent from companies like Netflix, Apple, Meta, Nike, Hulu, Uber, Amazon, Hypebeast, and Quibi, united by a shared passion for impact and excellence.
  • International team for global career growth.
  • Laptop and work equipment provided.
  • Beautiful working environment near Danang's city center (Dragon Bridge) and Hanoi office.

Health & Wellness

  • PVI health insurance program and annual health check-ups.
  • Active sports clubs (football, badminton, pickleball) and company retreats.
  • A modern pantry designed for relaxation and social connection.
  • Monthly wellness and learning workshops to recharge and grow.

More Info

Job Type:
Industry:
Function:
Employment Type:

About Company

Job ID: 150864513