Senior Forward Deployed Engineer, Agentic AI & RAG

Company
Braintrust is a global talent network that connects top independent professionals with leading companies for high-quality, flexible work. We help organizations hire skilled talent faster while giving professionals access to vetted opportunities with innovative teams.

Job description

About the Role

Lead the architecture and delivery of production Agentic AI and enterprise knowledge solutions for strategic customers. This role combines hands-on engineering, solution architecture, customer partnership, and delivery leadership across complex enterprise environments.

This is a remote U.S. contract role. Texas-based candidates are preferred, and the work requires up to 25% travel for customer engagements.

What You'll Do

• Translate ambiguous customer needs into scalable technical plans and successful AI deployments.
• Architect, prototype, implement, and optimize customer-specific applications on an Agentic AI platform.
• Build enterprise data pipelines, system integrations, multi-agent orchestration, RAG workflows, platform extensions, and production-grade AI services.
• Lead technical solution design with customers and partner closely with Product, Platform Engineering, and other cross-functional teams.
• Improve post-deployment reliability, observability, performance, adoption, and reusable delivery practices.

Requirements

• 6+ years of engineering experience, including at least 2 years in customer-facing, field engineering, solutions engineering, or forward-deployed engineering roles.
• Proven experience building and deploying production AI/ML, data-intensive, or enterprise-grade applications.
• Strong full-stack development experience with Python, Node.js or Go, and React or Vue.
• Hands-on DevOps experience with Docker, Kubernetes, CI/CD, and cloud-based deployment practices.
• Experience designing enterprise data pipelines, system integrations, REST APIs, SQL, GraphQL, webhooks, and reusable platform tooling.
• Strong knowledge of LLMs, prompt engineering and tuning, vector databases, RAG pipelines, and agentic workflows. Relevant tools may include Pinecone, Weaviate, AstraDB, LlamaIndex, Haystack, LangChain, LangGraph, or CrewAI.
• Ability to lead strategic customer implementations, translate uncertain business needs into actionable plans, and communicate effectively across technical and business stakeholders.
• An undergraduate, master's, or PhD degree in Computer Science, Data Science, or a related technical field.

Preferred Experience

• SLM fine-tuning, model distillation, or model optimization.
• Enterprise Agentic AI delivery, graph databases, multimodal AI, evaluation frameworks, security and guardrails, or GPU infrastructure.
• Production observability, monitoring, versioning, telemetry, trustworthy AI practices, and post-deployment optimization.
• Creating reusable technical assets, internal frameworks, documentation, or platform improvements.

Engagement and Selection

This is a full-time contract requiring 40 hours per week during Central Time business hours, with full working-hours overlap. The engagement is expected to begin as soon as possible and continue for at least six months. The selection process includes an initial HR screen, a technical screen, and two client interview rounds.

Compensation

$63-$84 USD per hour.