AI Engineer - Agentic Systems on W2 role

Role: Senior AI Engineer — Agentic Systems

Location: 5 days onsite – Plano, NY/NJ, Columbus

Duration: 12+ Months

Team: Customer-Facing AI Agents

The Opportunity

We are a technology organization operating at the scale of a major financial enterprise — and we are building AI agents that serve millions of customers directly. This is not a chatbot bolt-on or an innovation-lab experiment: our agentic platform sits in the production path of real customer conversations, with the reliability, latency, and safety bar that implies.

We're engaging senior engineers who have actually shipped agentic systems — people who have felt the difference between a demo that works and an agent that survives contact with real users. You'll join a small, senior team moving at startup pace with enterprise-scale distribution.

What You'll Do

• Design and build production agentic workflows for customer-facing use cases — multi-turn conversation, tool calling, retrieval, escalation, and human handoff.

• Own agent orchestration end to end using LangGraph/LangChain (or equivalent frameworks), including state management, guardrails, and failure recovery.

• Integrate agents with our core service layer: existing Java/Spring microservices, APIs, and event streams are the hands and feet of every agent you build.

• Build and tune the evaluation loop — automated evals, regression suites, trace analysis, and A/B measurement of agent quality.

• Work on the inference and serving layer: model routing, prompt/context management, and self-hosted serving with vLLM alongside commercial LLM APIs.

• Harden everything for a regulated, high-trust environment: PII handling, auditability, deterministic fallbacks, and observability.

Must-Have Qualifications

• 7+ years of software engineering experience, with senior/lead-level ownership of production systems.

• Proven hands-on delivery of LLM-based agentic systems in production — not coursework, not POCs. Expect to walk us through architecture, failure modes, and eval strategy of something you shipped.

• Strong Python (primary agent/ML stack) and Java (service integration) — both are daily-use languages here.

• Depth in the standard agent stack: LangChain, LangGraph, prompt/context engineering, tool/function calling, RAG pipelines.

• Working knowledge of PyTorch and model fundamentals — enough to fine-tune, debug model behavior, and reason about tradeoffs.

• Experience with LLM serving/inference — vLLM or comparable (TGI, TensorRT-LLM), plus commercial APIs (OpenAI, Anthropic, Bedrock/Vertex).

• Solid distributed-systems fundamentals: APIs, queues, caching, observability, CI/CD.

Major Plus

• Hands-on experience with agent-builder platforms such as Sierra or Decagon — deploying, extending, or evaluating them for customer-service use cases.

• Voice agents, real-time/streaming inference, or contact-center integration.

• Experience in regulated industries (finance, healthcare) — model risk, compliance review, audit trails.

• Eval frameworks (LangSmith, Braintrust, custom harnesses) and LLM safety/guardrail tooling.