Senior AI/ML Engineer: LLM & Agent Orchestration

Truefoundry; New York (NY); Ibrido; USD 180.000 - 230.000; Tempo pieno

Vantaggi offerti da questo lavoro

Health insurance

401(k)

Hybrid work

Lunch and snacks

Office access

Descrizione del lavoro

TrueFoundry is seeking a Senior AI/ML Engineer—LLM & Agent Stack (Customer-Facing) to join our team in New York. You will design core components enabling enterprise customers to run production agentic AI safely and efficiently, including multi-step agent orchestration, model routing, and governance.

You’ll work closely with customers and integrate tools like LangGraph, LangChain, and vector stores, while mentoring junior engineers and shaping product features for scalable AI workloads.

Competenze

• 5–10 years of software engineering with distributed systems, infra, or ML platforms.
• Deep practical experience deploying LLMs in production (RAG, embeddings pipelines).
• Hands-on experience with agent orchestration frameworks (LangGraph / LangChain) and stateful workflow design.

Mansioni

• Architect scalable agent orchestration patterns for production workloads.
• Own integrations: model adapters, LLM gateway hooks, vector DBs, tools & external APIs.
• Build and improve tracing, benchmarking and observability for LLMs and agents.
• Drive design for safety/guardrails: moderation hooks, human-in-the-loop checkpoints, audit trails.
• Mentor junior engineers, run design reviews, and improve engineering practices.
• Work with strategic customers to prototype complex agentic solutions.

Conoscenze

Distributed systems

LLMs in production

Agent orchestration

Kubernetes

Observability & cost controls

Strumenti

LangGraph

LangChain

Vector stores

Descrizione del lavoro

TrueFoundry is seeking a Senior AI/ML Engineer—LLM & Agent Stack (Customer-Facing) to join our team in New York. You will design core components enabling enterprise customers to run production agentic AI safely and efficiently, including multi-step agent orchestration, model routing, and governance.

You’ll work closely with customers and integrate tools like LangGraph, LangChain, and vector stores, while mentoring junior engineers and shaping product features for scalable AI workloads.