Forward Deployed Engineer

Project Info

The Forward Deployed Engineer builds and delivers production-grade, AI-powered systems directly with customers. This is a builder role: you will write, ship, and operate code in real customer environments. You bridge product intent, engineering execution, and real-world deployment, owning solutions end to end.

From discovery through production, you make sure the agentic system delivers measurable customer and business impact.

Responsibilities

Design and deploy production AI systems

• Design, build, and deploy production-ready AI systems in real customer environments.
• Implement agentic AI solutions: RAG and retrieval, orchestration, tool and function calling, and multi-step workflows.
• Translate ambiguous customer problems into shippable technical architectures with clear trade-offs.
• Move solutions from proof of concept to production with measurable adoption.
• Engineer for enterprise-grade quality: secure, scalable, observable, and resilient.

Prove the system works, and keep proving it

• Build the evaluation harness: baseline quality metrics, regression gates, safety checks, and offline evaluations before anything ships.
• Establish deployment patterns, evaluation loops, and monitoring frameworks that survive after you leave.
• Implement reliability patterns: retries, fallbacks, idempotency, and safe failure modes for agentic workflows.
• Instrument traces, dashboards, and alerts covering reliability, latency, and cost per outcome.
• Tune for performance and economics without trading away quality.

Build with AI coding agents, and be the editor of what they produce

• Command specialized AI coding agents—Cursor, GitHub Copilot, Devin, and custom LLM scripts—as junior developers, then refine their output into robust, maintainable production code.
• Act as technical editor for AI-generated code: catch the specific failure modes that LLMs introduce before they reach production.
• Evaluate delivered customer systems for accuracy, grounding, and safety; review AI-agent code for LLM-specific mistakes.

Own the security posture of what you ship

• Apply OWASP practices, secrets management, rigorous input validation, and authentication and authorization correct by default.
• Implement LLM-specific defenses for prompt injection, access controls, and PII boundaries between customer data and the model.
• Apply security and privacy fundamentals in implementation, not merely as documented intent.

Own end-to-end customer delivery

• Lead delivery from discovery and architecture through rollout, iteration, and operational readiness.
• Make pragmatic architectural decisions under delivery pressure and inside a customer’s existing stack.
• Build and maintain integration plumbing across APIs, identity, data sources, legacy systems, and observable data flow.
• Measure success by delivered impact and adoption.

Communicate at customer and executive altitude

• Explain architecture, risks, and constraints to executives and non-technical stakeholders in decision-ready language.
• Frame decisions across scope, reliability, speed, and cost; push back constructively when requests and constraints do not fit.

Transition delivery into durable ownership

• Hand over systems that operate without you, with clear ownership, documentation, monitoring, and support and iteration plans.
• Mentor engineers in production-grade AI delivery practices and reusable reference architectures.
• Capture reusable patterns as accelerators and playbooks for future deployments.

Requirements

• 7+ years in software engineering, architecture, or technical delivery at Senior Developer or Technical Team Lead level, with a strong record of shipping production systems.
• Demonstrated discovery-to-deployment work in enterprise customer environments.
• Hands-on backend and integration engineering with REST/GraphQL APIs, services, data integrations, Python, and Node.js.
• Strong debugging skills.
• Experience building LLM applications with LLM APIs, preferably Anthropic/Claude, tool calling, RAG, orchestration, and evaluation and quality gates.
• Proven AI-first engineering workflow, using AI coding agents and reviewing their output.
• Ability to review, refactor, and harden LLM-generated code to enterprise standards.
• Production discipline: zero-downtime mindset, CI/CD, environments, containerization with Docker and Serverless, robust logging, database migrations, rollback procedures, and incident response.
• Hands-on experience with at least one of AWS, Azure, or GCP.
• OWASP fluency and secure implementation of secrets handling, sensitive-data protection, input validation, authentication, authorization, and PII handling.
• Ability to lead technical conversations with non-technical stakeholders and translate trade-offs for decision-makers.
• Willingness to travel up to 70%.

Benefits

• General benefits depending on the form of employment.
• Hybrid work model combining office and remote work.
• Attractively located office with collaboration spaces.
• Onsite parking for employees.
• Referral program with financial bonus.
• Life insurance.
• Development budget, including language courses and other learning, plus a clear career path and international experience.
• Access to an internal learning platform with professional-growth training.
• Access to the MyBenefit platform, including Multisport.
• Team-building activities and charity initiatives.
• Working environment promoting diversity and inclusion.
• Private medical care: Platinum Package.