Senior AI Engineer Agentic Systems

Gov Services Hub; New Jersey; On-site; USD 180,000 - 240,000; Full time

Job summary

Gov Services Hub in the United States seeks a Senior AI Engineer to join the Customer-Facing AI Agents team on a 12-month contract, onsite across multiple locations. You will design production agentic workflows, orchestrate agents end-to-end, and integrate with Java/Spring services.

The role requires hands-on delivery of LLM-based agentic systems, strong Python/Java, LangChain/LangGraph expertise, and experience with PyTorch and LLM serving in regulated environments.

Qualifications

• 7+ years of software engineering experience with senior/lead ownership of production systems.
• Proven hands-on delivery of LLM-based agentic systems in production, with architecture, failure modes, and eval strategy.
• Strong Python and Java for daily use.
• Depth in LangChain, LangGraph, prompt/context engineering, tool/function calling, and RAG pipelines.
• Working knowledge of PyTorch and model fundamentals.
• Experience with LLM serving/inference (vLLM, TensorRT-LLM) and commercial APIs (OpenAI, Anthropic, Bedrock/Vertex).
• Solid distributed-systems fundamentals: APIs, queues, caching, observability, CI/CD.

Responsibilities

• Design and build production agentic workflows for customer-facing use cases.
• Own agent orchestration end-to-end using LangGraph/LangChain, including state mgmt, guardrails, and recovery.
• Integrate agents with core service layer: Java/Spring microservices, APIs, event streams.
• Build and tune the evaluation loop: automated evals, regressions, trace analysis, A/B measurement.
• Work on inference and serving: model routing, prompt/context management, self-hosted serving with vLLM and external APIs.
• Harden systems for regulated environments: PII handling, auditability, deterministic fallbacks, observability.

Skills

Python

Java

LangChain

LangGraph

Prompt engineering

RAG pipelines

PyTorch

LLM serving

CI/CD

Tools

vLLM

TensorRT-LLM

OpenAI API

Anthropic API

Bedrock/Vertex

Job description

Senior AI Engineer - Agentic Systems (Contract)

Level: Senior Engineer (VP-equivalent)

Engagement: 12-month contract (W2, extension possible

Location: Fully onsite - [plano, NY, NJ, Columbus]

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.

Skill (optional)

Level (optional)

Criteria (optional)

LangChain

Advanced (6-9 years experience)

Required

• GenAI Prompt Engineering
• Advanced (6-9 years experience)
• Pytorch
• Advanced (6-9 years experience)
• OpenAI Engineering
• Advanced (6-9 years experience)
• Testing DevOps & CICD
• Advanced (6-9 years experience)