AI Language Engineer

Cresta Cresta · Vertical AI · United States · Remote · Engineering

AI Language Engineer to design, build, and enhance natural language systems for intelligent products and experiences in text and speech domains. This role involves linguistic insight, applied NLP expertise, and AI engineering execution, collaborating with product and engineering teams to translate language challenges into scalable AI solutions. Responsibilities include developing LLM workflows, NLP components (intent detection, entity recognition, RAG), ASR/TTS workflows, fine-tuning and evaluating models, analyzing model outputs, defining linguistic evaluation criteria, and driving R&D for speech and language systems. The role also involves data preprocessing, dataset creation, designing experiments, integrating models into production systems, building tooling for evaluation and monitoring, supporting optimization and infrastructure, and collaborating cross-functionally.

What you'd actually do

  1. Design, develop, and refine large language model (LLM) workflows, including context engineering, prompt design, and evaluation frameworks to steer and improve model behaviors.
  2. Build language processing components for features such as intent detection, entity recognition, summarization, retrieval-augmented generation (RAG), and conversational response quality.
  3. Develop speech-to-text (ASR) and text-to-speech (TTS) workflows and evaluation frameworks, bridging audio-feature/signal-level processing with LLM-driven reasoning and orchestration.
  4. Fine-tune and evaluate models using quantitative and qualitative metrics to ensure robust performance across tasks.
  5. Collaborate with software developers to integrate language models into production systems and ensure scalable deployment.

Skills

Required

  • Python
  • NLP/AI frameworks (Hugging Face Transformers, TensorFlow, PyTorch)
  • data preprocessing
  • model evaluation
  • language dataset design
  • analytical skills
  • diagnose and communicate model behavior
  • linguistic patterns
  • performance trade-offs
  • collaboration and communication skills

Nice to have

  • multilingual NLP
  • cross-locale language modeling
  • linguistic analysis
  • discourse
  • semantics
  • speech processing (ASR/TTS)
  • audio feature pipelines
  • phonetics research
  • production deployments
  • ML ops
  • scalable systems
  • cloud environments (AWS, GCP, Azure)

What the JD emphasized

  • production systems
  • scalable deployment
  • ML ops

Other signals

  • LLM workflows
  • NLP components
  • speech-to-text (ASR) and text-to-speech (TTS) workflows
  • fine-tune and evaluate models
  • production systems
  • ML ops