Forward Deployed Engineer
fastino.ai
Forward Deployed Engineer
fastino.ai
Task-specific language models for enterprise AI
Full-time | San Francisco
We're building specialized, efficient language models that beat big general models on the tasks that matter. Our team includes alumni from Google Research, Apple, Stanford, and Cambridge.
Our open source GLiNER models have been downloaded 50M+ times and are used by teams at NVIDIA, Meta, and Airbnb.
We've raised $25M (covered in TechCrunch) from Microsoft, Khosla Ventures, Insight Partners, GitHub CEO Thomas Dohmke, Docker CEO Scott Johnston, and others.
You'll be the engineer who sits inside our customers' stacks and gets them running in production. If you like hard technical problems and talking to the people who have them, this is for you.
Embed with customer engineering teams to scope, build, and deploy Fastino models into their production systems.
Write real code: integrations, data pipelines, eval harnesses, and services that run on customer infra (cloud, VPC, on prem).
Fine-tune and evaluate models on customer data, and prove they beat the baseline on accuracy, latency, and cost.
Debug the messy stuff: auth, networking, GPU and inference performance, data quality, weird edge cases.
Own the technical side of deals from first call through go-live, working closely with our founders and AEs.
Turn what you build in the field into reusable tools, reference architectures, and SDK improvements.
Bring customer feedback straight to research and product, and push for what customers actually need.
BS or MS in Computer Science or a related field (or equivalent experience).
3+ years as a software engineer, ideally with some time in a customer facing role (FDE, solutions engineering, consulting, or similar).
Strong in Python. Comfortable with at least one of TypeScript, Go, or Rust.
Hands on experience shipping LLM or ML systems to production: APIs, fine-tuning, evals, RAG, or agents.
Solid with cloud and infra basics: AWS/GCP/Azure, Docker, Kubernetes, networking, and security.
Clear communicator who can explain tradeoffs to an engineer and a VP in the same meeting.
Ownership mindset. You'd rather fix it yourself than file a ticket.
Bonus: experience with GLiNER, NER, or other information extraction models.
Bonus: early stage startup experience.
Willing to travel to customer sites as needed.
Task-specific language models for enterprise AI
Fastino builds Task-Specific Language Models (TLMs) tailored to enterprise tasks like summarization, JSON conversion, PII redaction, and agentic function calling. The models run on CPUs or NPUs with near-instant inference, avoiding the need for expensive GPU clusters, and are accessed via a TLM API with a flat monthly subscription (including a free developer tier). Deployment is flexible: customers can run the models in their VPC, on-premise, or at the edge to keep data under their control and improve security. The company aims to deliver efficient, accurate AI tools that fit into enterprise workflows with predictable pricing and strong data security.
Explore more opportunities at fastino.ai