AI Engineer - Senior

NENI TECHSYSTEMS INC. is hiring a Senior AI Engineer (Agentic Systems) to design, build, and deploy production-grade large language model and agentic AI solutions. This is an onsite opportunity based in Plano, TX (also listed for Columbus, OH , New York, NY , and Jersey City, NJ ), with a focus on delivering LLM-based agent systems that operate reliably in production environments.

The role emphasizes hands-on engineering across the full lifecycle of agentic systems, from orchestration and retrieval to evaluation, testing, and operational readiness, with a preference for candidates familiar with regulated domains such as Banking/Financial Services .

Responsibilities

• Build and deploy production-grade LLM and agentic AI systems .
• Deliver LLM-based agentic systems in production.

Requirements

• 7+ years of software engineering experience, with senior or lead-level ownership.
• Proven experience delivering LLM-based agentic systems in production.
• Strong hands-on experience with Python and Java/Spring .
• Expertise with LangChain , LangGraph , or equivalent agent orchestration frameworks.
• Experience with RAG , tool/function calling, multi-turn conversations, escalation, and human handoff.
• Strong understanding of prompt/context engineering and agent state management .
• Experience with LLM evaluation , regression testing , trace analysis , and A/B testing .
• Hands-on experience with vLLM or comparable LLM inference/serving platforms and commercial LLM APIs.
• Working knowledge of PyTorch and LLM/model fundamentals.
• Strong distributed systems experience including APIs, queues, caching, observability, and CI/CD .
• Experience implementing guardrails , PII handling , auditability , deterministic fallbacks , and production reliability.
• Local to the selected location (within approximately 30–40 miles ) and able to work onsite ; no relocation candidates.
• Available for an onsite interview .

Preferred

• Experience with agent-building platforms such as Sierra or Decagon .
• Voice agents, streaming inference, or contact-center integrations.
• Experience with banking, financial services, healthcare, or other regulated-industry environments.
• Experience with LangSmith , Braintrust , or custom LLM evaluation frameworks.
• Knowledge of LLM safety and guardrail technologies.

Technologies

• Python , Java , Spring
• LangChain , LangGraph
• RAG , vLLM , PyTorch
• CI/CD

Work Arrangement

• Onsite (in person) with an onsite interview requirement.
• Locations: Plano, TX / Columbus, OH / New York, NY / Jersey City, NJ .

Pay and Hours

• $55.00 - $75.00 per hour
• 40.0 hours per week

Visa

• USC , EAD , H1B