Founding Forward Deployed Engineer

Overview

Gimlet Labs is building the foundation for the next generation of AI applications. As generative AI workloads rapidly scale, inference efficiency is becoming the critical bottleneck. Gimlet is redefining AI inference from the ground up, combining cutting-edge research with an integrated hardware-software stack that delivers breakthrough performance, efficiency, and model quality.

Gimlet pairs its inference stack with a seamless developer experience, allowing users to deploy, manage, and monitor AI workloads from frameworks like PyTorch and Lang Chain at production scale in seconds. The founding team has deep experience across AI, distributed systems, and hardware with previous successful exits.

We are seeking our very first Forward Deployed Engineer to work hands-on with our customers, solving complex AI inference challenges and building production-grade ML solutions on the Gimlet platform. This is a deeply technical role where you'll partner directly with ML engineers at cutting-edge AI companies to optimize model performance, architect inference pipelines, and push the boundaries of what's possible with our technology.

This role is ideal for engineers who thrive at the intersection of systems engineering and applied ML, who want direct exposure to how companies are actually deploying AI in production, and who are energized by solving hard technical problems with immediate customer impact.

• Partner with customers to architect and build production AI inference pipelines on the Gimlet platform, optimizing for latency, throughput, and cost.

• Implement and optimize model deployments including LLMs, diffusion models, and custom architectures using techniques like quantization, batching, and caching.

• Debug complex performance issues across the full stack—from model architecture to GPU kernels to networking.

• Build reference implementations, technical content, and tooling that showcase Gimlet's capabilities, design and run sophisticated demos and POCs.

• Create evaluation and benchmark harnesses, regression checks that preserve model quality as performance improves.

• Deliver actionable, high-impact feedback to internal teams to drive platform improvements aligned with customer needs.

• Build and maintain trusted relationships with customer leaders and stakeholders to ensure successful deployment and scaling.

• Hands-on experience with production ML model deployment, inference optimization, or ML infrastructure

• Familiarity with the AI/ML stack:
  PyTorch, transformers, LLM serving frameworks (vLLM, Tensor
  
  RT-LLM, TGI), or similar

• Experience with infrastructure services (e.g., Kubernetes, SLURM), infrastructure-as-code tools (e.g., Ansible), container platforms (e.g., Docker), scripting/programming languages (e.g., Python), and observability, tracing/logging tools.

• Strong understanding of GPU computing, model optimization techniques (quantization, batching, KV caching), and distributed systems fundamentals

• Ability to debug complex technical issues across hardware and software layers

• Strong written and verbal communication skills—you can explain complex technical concepts clearly

• Comfort with ambiguity and a bias toward action in a fast-paced startup environment

• Contributions to open-source ML projects or frameworks.

• Experience with AI accelerators, custom hardware, or datacenter infrastructure

• Background in performance engineering, profiling, or low-level optimization.