Forward Deployed AI Engineer (London)
Edra5 days ago
Location
London
Type
Full Time
Salary
GBP 120,000 – 180,000
Level
Mid
Role
AI Engineer
Posted
Jul 20, 2026
Full TimeMid
The role
Summary
Edra, a Series A AI startup backed by Sequoia, is seeking a Forward Deployed AI Engineer in London to build and deploy complex LLM-based systems and multi-agent architectures that teach enterprise AI agents how businesses actually operate. This role combines hands-on engineering with direct customer engagement, requiring 3+ years of production AI experience, expertise in LLM orchestration, agentic systems, and the ability to navigate from research concepts to scalable production deployments.
What you'll do
Enterprise Customer Engagement & Solution Design: Work directly with enterprise customers to understand operational workflows, identify automation opportunities, prototype solutions, and drive adoption from discovery through production scaling. Own the complete technical journey including problem identification, solution architecture, production deployment, and impact expansion.
LLM System Architecture & Development: Design and implement production-grade LLM-powered systems and agentic workflows from concept through scalable deployment. Build complex multi-layer systems handling millions of requests, demonstrating deep architectural decisions and engineering trade-offs.
Agentic Systems & Autonomous Operations: Develop intelligent agents for autonomous knowledge management including systems that can edit, update, and maintain large knowledge bases independently. Build agents capable of learning from enterprise data sources including knowledge bases, conversations, tickets, and system logs.
Reliability & Confidence Frameworks: Design and implement evaluation frameworks, confidence scoring systems, and decision logic that determines when to automate versus escalate to human operators. Build systems that generate written instructions agents can execute with measurable confidence levels.
Platform Contribution & Context Learning: Extend and leverage the core context-learning library to solve customer-specific problems while contributing reusable capabilities, frameworks, and lessons back to the platform. Ensure solutions can be generalized for future customer deployments.
Scalable System Architecture: Architect asynchronous, scalable systems capable of complex AI orchestration and human-in-the-loop workflows. Build systems optimized for context engineering, prompt optimization, and continuous improvement mechanisms.
What we look for
Technical
Production LLM Systems DevelopmentDemonstrated experience building complex, production-grade LLM-based systems with multiple engineering layers and architectural decisions. Must have shipped meaningful products with real-world complexity and understand LLM orchestration patterns, prompt engineering, and model integration challenges.
Multi-Agent & Autonomous SystemsHands-on experience designing and implementing multi-agent architectures and autonomous systems in production environments. Understanding of agent coordination, state management, and complex orchestration workflows.
Evaluation & Confidence SystemsExperience building evaluation frameworks, confidence scoring mechanisms, and fallback logic for AI systems. Familiarity with reliability patterns, uncertainty quantification, and human-in-the-loop decision systems.
Scalable Backend ArchitectureStrong foundation in asynchronous systems, distributed computing, and scalable backend design capable of handling high-throughput AI workloads. Experience with event-driven architectures and complex system orchestration.
Context Engineering & OptimizationPractical experience with prompt optimization, context engineering, and techniques for improving LLM performance over time. Understanding of how systems learn and improve through human-in-the-loop feedback and iterative refinement.
Education
Bachelor's Degree in Computer Science or Related FieldA foundational degree in computer science, software engineering, mathematics, or equivalent discipline providing core algorithmic and systems thinking capabilities.
Advanced Study in Machine Learning or AI (Preferred)Formal education or significant self-directed learning in machine learning, deep learning, or artificial intelligence concepts. Comfort navigating research papers and translating theoretical concepts into production implementations.
Experience
3+ Years of Professional Software EngineeringMinimum 3 years of professional software development experience, with demonstrated progression in complexity and scope of systems built.
2+ Years with Production LLM or AI SystemsSubstantial hands-on experience shipping production machine learning or AI systems at scale. Should include experience scaling complex AI workflows and managing production ML infrastructure.
Enterprise Software or Customer-Facing EngineeringBackground building solutions for enterprise customers or shipping customer-facing products. Ability to balance technical depth with commercial judgment and customer empathy.
Skills
Required skills
Python ProgrammingExpert-level Python development for building production AI systems, data processing pipelines, and complex business logic. Essential for LLM system development and ML infrastructure.
LLM API Integration & OrchestrationProficiency with large language model APIs (OpenAI, Anthropic, Google, open-source models) and frameworks for chaining, orchestrating, and managing LLM workflows in production environments.
System Design & ArchitectureAbility to design scalable, maintainable system architectures handling complex requirements. Experience with async patterns, state management, and distributed system considerations for AI applications.
Software Engineering Best PracticesStrong fundamentals in testing, code quality, version control, CI/CD, and production deployment practices. Commitment to building reliable, maintainable systems with proper monitoring and observability.
Problem-Solving & Technical CommunicationAbility to break down open-ended problems, prototype solutions iteratively, and clearly communicate complex technical concepts to both technical teams and non-technical stakeholders.
Nice to have
LangChain, LlamaIndex, or Agent FrameworksExperience with popular AI orchestration frameworks and agent-building libraries that accelerate LLM application development and multi-step reasoning systems.
RAG (Retrieval-Augmented Generation) SystemsHands-on experience building retrieval-augmented generation systems that combine knowledge bases with LLM reasoning, including vector databases and semantic search implementations.
Fine-tuning & Model CustomizationExperience fine-tuning LLMs for specific domains or tasks, or experience optimizing model performance through prompt engineering, in-context learning, and other adaptation techniques.
Data Pipelines & ETLExperience building data ingestion and transformation pipelines that process diverse data sources (conversations, tickets, logs, knowledge bases) into structured formats for AI systems.
Prompt Engineering & LLM AnalysisDeep expertise in prompt design, few-shot learning, chain-of-thought reasoning, and techniques for analyzing LLM behavior and improving reliability and accuracy.
Observability, Monitoring & LLMOpsExperience instrumenting AI systems for production monitoring, debugging LLM behavior, tracking model performance over time, and implementing LLMOps practices.
Evaluation Metrics & ML TestingFamiliarity with building custom evaluation frameworks, defining quality metrics for AI systems, and implementing automated testing for machine learning pipelines.
TypeScript or Async Backend FrameworksProficiency with backend technologies like Node.js, FastAPI, or async Python frameworks useful for building responsive, scalable AI service architectures.
Compensation & benefits
Salary
GBP 120,000 – 180,000 (annual)
Stock options
Available
Benefits
Learning & Development
Access to learning resources, conferences, and opportunities to work at the cutting edge of AI and machine learning. Exposure to both research and production engineering at a Series A startup.
Equity Participation
Meaningful equity stakes typical for Series A startup positions. Opportunity to benefit from company growth backed by top-tier investors including Sequoia.
Flexible Work Arrangement
Remote-friendly work environment with option to work from London office or hybrid arrangement. Access to well-resourced engineering environment.
High-Impact Projects
Work directly with enterprise customers on meaningful, high-impact problems. Ability to see your work adopted and creating real business value quickly.
Talented Team & Mentorship
Work alongside experienced AI researchers, engineers, and strategists from companies like Palantir and other leading organizations. Access to deep technical expertise and mentorship.
Technical Leadership
Ownership of complete technical projects and customer relationships. Opportunity to make architectural decisions and guide technical direction.
Interview process
- 1Initial Screen with Recruiter — Brief conversation to discuss your background, experience with production LLM systems, and interest in the Forward Deployed Engineer role. Focus on understanding your deployment and scaling experience.
- 2Technical Conversation with Engineer — Deep-dive technical discussion where you'll walk through a complex LLM system you've built, discussing architectural decisions, challenges overcome, and lessons learned. Expect questions on agentic systems, evaluation frameworks, and production reliability patterns.
- 3System Design & Architecture Assessment — Collaborative discussion on how you would architect a complex AI system. May include designing for enterprise scale, handling uncertainty in LLM outputs, or building context-learning features.
- 4Customer-Facing Skills Evaluation — Conversation with someone from customer-facing team to assess communication skills, customer empathy, and ability to navigate ambiguity and unclear requirements with commercial judgment.
- 5Founder/Leadership Conversation — Discussion with founder or technical leadership about vision, your excitement for the problem space, and fit with Edra's culture of intensity and self-direction.
- 6Reference Checks — References from previous roles, particularly those involving production AI systems, customer engagement, or leadership of complex technical projects.
Apply for this position
You'll be redirected to the company's application page
Edra
View all jobs
Edra is an artificial intelligence company that develops advanced AI solutions and platforms. The company focuses on creating intelligent systems and tools that help businesses leverage machine learning and artificial intelligence technologies. Operating in the competitive AI and software market, Edra aims to provide accessible and powerful AI capabilities to organizations seeking to enhance their operations and decision-making processes through data-driven insights and automation.
edra.ai
Tech Stack
Languages
PythonTypeScript or JavaScriptSQL
Frameworks
LangChainLlamaIndexFastAPIPydantic
Databases
Vector Databases (Pinecone, Weaviate, Milvus)PostgreSQLRedis
Tools
OpenAI API / LLM APIsGit & GitHubDocker & ContainerizationMonitoring & Observability (DataDog, New Relic, Prometheus)CI/CD Platforms (GitHub Actions, GitLab CI)
Other
Prompt Engineering TechniquesHuman-in-the-Loop SystemsAgentic AI & Autonomous SystemsEnterprise Integrations & APIs