Senior AI Engineer - Forward Deployed (FDE)
About The Position
We are seeking a Senior AI Engineer with a unique background: extensive experience (8-12 years) as a serious software engineer, particularly in building cloud-native systems and platforms on AWS, combined with recent, in-depth experience (within the last year) building AI systems like agents, RAG systems, and LLM-powered applications. The role emphasizes solving the engineering challenges in AI, such as reliability, cost, latency, security, and evaluation of non-deterministic systems. The engineer will work across the full stack, shipping AI capabilities in the product and building underlying platform primitives like model access, agent orchestration, retrieval, and evaluation. This is a senior individual contributor role focused on leading by building. As a forward-deployed engineer, you will embed with enterprise clients to make AI work within their environments and bring field learnings back to improve the product and platform.
Requirements
- 8-12 years of software engineering experience, with significant time building cloud-native systems, backend services, or platforms; platform engineering background strongly preferred.
- Deep, hands-on AWS expertise: EKS/ECS, Lambda and serverless patterns, IAM and networking, and infrastructure-as-code (Terraform or CDK).
- Experience operating real production services with real SLOs.
- Strong Python skills and production engineering habits: testing, code review, observability, and clean design.
- Solid grounding in distributed systems, API design, and event-driven architecture.
- Recent, demonstrable AI depth (within roughly the last year) through hands-on building of agents, RAG pipelines, or LLM applications.
- Working experience with at least one agent framework (LangGraph, CrewAI, or comparable) and major model APIs (Anthropic, OpenAI, Bedrock).
- Practical understanding of LLM behavior: context management, token economics, cost/latency trade-offs, and handling non-determinism in testing and shipping.
- Good understanding of RAG, with a focus on retrieval and its measurement.
- Familiarity with MCP, including its limitations and security considerations.
- Experience integrating with enterprise systems (identity/SSO, enterprise APIs, data platforms, systems of record) and working within enterprise security, network, and compliance constraints.
- Customer-facing engineering skills: credibility with client architects and business owners, ability to run demos and discovery sessions, and communicate trade-offs clearly.
Nice To Haves
- Experience building or operating a model/LLM gateway or proxy layer.
- Model serving experience (vLLM, GPU scheduling, inference optimization).
- Experience with guardrails, prompt-injection defense, or LLM security (OWASP LLM Top 10).
- TypeScript for product-surface work.
- Prior startup experience.
- Prior forward-deployed, solutions engineering, or technical consulting experience with enterprise customers.
- Experience delivering customer-deployable software (single-tenant, customer-VPC, or on-prem models).
Responsibilities
- Design, build, and ship agents, agentic workflows, and LLM-powered features from prototype to production.
- Build robust retrieval systems, including chunking and embedding strategies, vector search, hybrid search, and re-ranking, with honest measurement of quality.
- Integrate models and tools cleanly, including major model APIs (Anthropic, OpenAI, Bedrock) and tool/data access via the Model Context Protocol (MCP), addressing security considerations.
- Embed with client teams to conduct technical discovery, map workflows and systems, and shape AI solutions for their environments.
- Build and ship AI solutions within customer environments, integrating with enterprise systems like identity/SSO, enterprise APIs, data warehouses, legacy databases, and systems of record (Salesforce, ServiceNow, SAP).
- Deploy into customer AWS accounts, private VPCs, and restricted networks, designing for their security models.
- Act as the technical face of the company on-site, running working sessions and demos with client engineers and business stakeholders, and navigating enterprise InfoSec and architecture reviews.
- Translate field learnings into product and platform improvements.
- Build the model-access layer, including a unified interface across providers, routing, caching, rate limits, and cost tracking.
- Develop agent orchestration and lifecycle plumbing, including state, memory, retries, guardrails, versioning, and rollback.
- Establish an evaluation harness with automated evals and regression tests integrated into CI/CD.
- Implement comprehensive instrumentation for tracing, cost/latency dashboards, and quality monitoring.
- Own AWS infrastructure for AI workloads, including EKS/ECS, Lambda, IAM, networking, and infrastructure-as-code.
- Operate built systems, including production ownership, on-call responsibilities, and performance/cost tuning.
- Drive design reviews and set technical patterns, making architecture calls and defending trade-offs.
- Mentor 1-2 engineers and improve the team's AI engineering practices.
- Make pragmatic build-vs-buy decisions.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
