Senior ML Platform Engineer - Production-Ready AI Systems

Invoca; Austin (TX); Remote; USD 152,000 - 228,000; Full time

Benefits offered by this job

Flexible Time Off

Health benefits

Stock options

401(k) match

Job summary

Invoca is hiring a Senior ML Engineer to own the production ML stack, turning trained models into reliable, high-throughput services used by product teams. You’ll partner with Data Scientists and Applied AI Engineers to ship AI-powered features at scale.

You will own inference infrastructure, optimize latency and throughput, and drive end-to-end ML pipelines, serving models via APIs and monitoring to ensure reliability and speed.

Qualifications

• 5+ years of ML Engineering with production focus.
• Advanced Python and DL proficiency (PyTorch, Transformers, spaCy).
• Experience deploying transformer-based NLP models in production.
• Fine-tuning SLMs/LLMs (LoRA, QLoRA, PEFT) with optimizations.
• Proficiency with inference infra: Triton, Baseten, vLLM, TGI, SageMaker or Vertex AI.
• Building production-grade ML APIs for downstream consumers.
• Familiarity with MLOps tooling (Braintrust, MLflow).
• Experience in agentic/multi-step AI workflows is a plus.
• Bachelor’s in CS/Engineering; advanced degree a plus.
• Familiarity with RLHF is a bonus.

Responsibilities

• Architect, implement, and maintain CI/CD pipelines for ML artifacts.
• Serve as SME for operational excellence across ML stack (uptime, latency, cost).
• Treat model serving as a product for internal customers and ensure shipping capability.

Skills

ML Engineering

Python & DL

Transformer NLP in production

Fine-tuning SLMs/LLMs

Inference performance

APIs for ML models

MLOps tools

Agentic AI workflows

B.S. in CS/Engineering

RLHF familiarity

Education

B.S. in Computer Science/Engineering

Tools

Triton Inference Server

Baseten

vLLM

TGI

SageMaker

Vertex AI

Braintrust

MLflow

Job description

Invoca is hiring a Senior ML Engineer to own the production ML stack, turning trained models into reliable, high-throughput services used by product teams. You’ll partner with Data Scientists and Applied AI Engineers to ship AI-powered features at scale.

You will own inference infrastructure, optimize latency and throughput, and drive end-to-end ML pipelines, serving models via APIs and monitoring to ensure reliability and speed.