Senior AI/ML Engineer — LLM & Agent Orchestration

Truefoundry; New York (NY); Vor Ort; USD 180.000 - 280.000; Vollzeit

Benefits dieser Stelle

Health insurance (family)

401(k) retirement plan

Hybrid work: Tue/Wed in office

Lunch & snacks provided

Office flexibility (London/India)

Zusammenfassung

TrueFoundry in New York is seeking a Senior AI/ML Engineer—LLM & Agent Stack (Customer-Facing) to design and own core components enabling enterprise production agentic AI. You will build robust orchestration for multi-step agents, model routing, observability, policy enforcement, and integrate LangGraph, LangChain, and vector stores.

This is a customer-facing role where you'll work with enterprise clients and may write code in their environments to prototype scalable solutions that are safe and

Qualifikationen

• 5–10 years of software engineering experience with distributed systems or ML platforms.
• Production experience deploying LLMs (RAG, embeddings pipelines).
• Hands-on with agent orchestration frameworks and stateful workflows.
• Strong systems knowledge: Kubernetes, containers, service meshes, performance tuning.
• Proven observability, cost controls, and policy enforcement for production services.

Aufgaben

• Architect scalable agent orchestration patterns for production workloads.
• Own integrations: model adapters, LLM gateway, vector DBs, tools, APIs, and LLMops flows.
• Improve tracing, benchmarking, observability for LLMs and agents.
• Drive safety/guardrails design, moderation hooks, and audit trails.
• Mentor junior engineers and lead design reviews.
• Work with strategic customers to prototype agentic solutions.

Kenntnisse

Distributed systems

LLM integration

Agent orchestration

Kubernetes

Observability & cost controls

Tools

LangGraph

LangChain

Vector stores

Jobbeschreibung

TrueFoundry in New York is seeking a Senior AI/ML Engineer—LLM & Agent Stack (Customer-Facing) to design and own core components enabling enterprise production agentic AI. You will build robust orchestration for multi-step agents, model routing, observability, policy enforcement, and integrate LangGraph, LangChain, and vector stores.

This is a customer-facing role where you'll work with enterprise clients and may write code in their environments to prototype scalable solutions that are safe and