An application made for this job — a tailored resume and cover letter that speak straight to the posting.
CyberCoders in Manhattan, NY is seeking a Senior AI Engineer to lead the design and deployment of LLM-powered systems, from prototype to production. You will build end-to-end features, architect RAG pipelines, and develop multi-model agent frameworks with strong emphasis on safety, observability, and cost-efficient scaling.
You will collaborate with product, design, security, and domain experts to translate business requirements into technical specs and mentor junior engineers in best practices
Senior AI Engineer - LLM Systems
We are building production-grade AI products that tackle complex, high-stakes problems in (fintech / accounting / legaltech), and we need a senior engineer who can take LLM-powered systems from prototype all the way to reliable, monitored, production services - not just demos.
Design and ship end-to-end LLM-driven features and services using clean-code, CI/CD, and observability best practices
Architect and build retrieval-augmented generation (RAG) pipelines and vector retrieval systems that stay accurate, low-latency, and fresh
Develop agent frameworks and tool-calling pipelines that coordinate multiple models and external systems for complex multi-step workflows
Define and run evaluation frameworks - automated evals, human-in-the-loop annotation, and regression suites - to measure accuracy, safety, and bias
Instrument production models with monitoring, alerting, and A/B testing to catch regressions before users do
Partner with product, design, security, and domain experts to translate business requirements into actionable technical specs
Mentor engineers through code reviews and establish best practices for model development, deployment, and post-deployment maintenance
5+ years of production backend or systems engineering experience; strong Python and modern practices (testing, CI/CD, containerization)
Hands-on experience with LLMs and transformer architectures including fine-tuning, prompt engineering, or adapting foundation models for production
Demonstrated experience designing and integrating retrieval systems (vector databases, dense/sparse retrieval, similarity search) with LLMs
Practical experience building agent and tool-calling pipelines with multi-step orchestration and state management
Experience with cloud platforms (AWS, GCP, or Azure), MLOps tooling, and cost-effective inference scaling
Domain experience in fintech, accounting, audit, or legaltech - especially regulatory, privacy, or compliance considerations
Familiarity with specific tooling: LangChain, LlamaIndex, Weaviate, FAISS, Pinecone, Ray, or MLflow
Experience designing human annotation workflows and managing eval suites at scale
Background collaborating with security and privacy teams to implement guardrails and access controls in regulated environments
$220k-$280k base - $300k-$600k Equity
Manhattan, NY - Onsite
Unlimited PTO
Wellhub Platinum membership
Comprehensive health, dental, and vision coverage
Free company dinner every day