Forward Deployed Engineer

# Forward Deployed Engineer

## About the role
A Forward Deployed Engineer works directly with customers to deploy, integrate, and adapt the company's AI products in their environments. The role combines software engineering with customer-facing problem solving, turning ambiguous business needs into production-grade AI solutions. You will act as the technical bridge between customers and the core product and research teams.

## Responsibilities
* Deploy and configure AI-powered products within customer environments
* Design and build AI solutions that address specific customer workflows
* Build custom integrations between the product and customer systems and data sources
* Translate customer requirements into technical designs and working prototypes
* Evaluate model and system quality on customer data, and iterate to improve accuracy and reliability
* Diagnose and resolve production issues on customer deployments
* Run technical discovery sessions and workshops with customer stakeholders
* Document deployments, integration patterns, and operational runbooks
* Relay customer feedback and recurring needs to product and engineering teams
* Contribute reusable components and tooling back to the core platform

## Required skills
* Strong Python
* Hands-on experience building applications with large language models
* Hands-on experience with retrieval-augmented generation (RAG) and vector search
* Strong prompt engineering and context design
* Experience evaluating LLM output quality (eval datasets, metrics, regression testing)
* Strong SQL
* Hands-on experience building and consuming REST APIs
* Experience deploying and troubleshooting production systems on a major cloud platform (AWS, Azure, or GCP)
* Excellent written and verbal communication with technical and non-technical audiences
* Experience working directly with customers or stakeholders

## Preferred skills
* Experience building agentic workflows and tool-calling systems
* Familiarity with fine-tuning or adapting open-weight models
* Experience with LLM observability and tracing
* Familiarity with guardrails, PII handling, and AI safety practices
* TypeScript or JavaScript
* Familiarity with data pipelines and ETL
* Kubernetes
* Experience in solutions engineering, consulting, or customer success engineering
* Willingness to travel to customer sites

## Tools we use
* Git
* Docker
* Jira
* Confluence
* Postman
* Terraform
* Slack
* LLM provider APIs (Anthropic, OpenAI)
* LangChain or LlamaIndex
* Vector databases (pgvector, Pinecone, Qdrant)
* Evaluation and tracing tools (LangSmith, Langfuse)

## Education
* Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience

## Certifications
* Cloud certification (AWS, Azure, or GCP) is a plus but not required