Senior AI Solutions Developer

Omiz Staffing Solutions (OSS); Rutherford (NJ); Hybrid; USD 130,000 - 185,000; Full time

Job summary

Omiz Staffing Solutions (OSS) seeks an experienced AI/LLM Software Engineer to design, develop, and deploy enterprise-grade AI applications, assistants, agents, and intelligent workflows. The ideal candidate will combine hands-on Python and software engineering with practical expertise in LLMs, RAG, agentic AI, and AI observability.

This role is highly collaborative and stakeholder-facing, requiring translating business requirements into secure, scalable AI solutions, APIs, databases, and

Qualifications

• 5–8 years of professional software engineering experience.
• Strong hands-on experience with Python and software development.
• Demonstrated experience building AI/LLM-powered applications in enterprise or production environments.
• Experience developing AI assistants, agents, agentic workflows, or LLM applications.
• Hands-on experience with MCP/FastMCP or similar tool-integration technologies.
• Experience with LangGraph or comparable AI/agent orchestration frameworks.
• Strong understanding of APIs, SQL, databases, and enterprise system integration.
• Experience implementing RAG solutions using structured and/or unstructured data.
• Experience with LangSmith, W&B, OpenTelemetry for monitoring/observability.
• Understanding of authentication, authorization, secure data access, and enterprise security practices.
• Strong understanding of AI governance, responsible AI, privacy, security, and HITL concepts.
• Excellent communication and stakeholder-management skills.
• Ability to work directly with customers/business stakeholders in a forward-deployed engineering capacity.

Responsibilities

• Design and develop enterprise AI/LLM applications, assistants, agents, and intelligent workflows.
• Build scalable, production-ready solutions using Python and modern software practices.
• Develop agentic AI workflows using LangGraph or similar orchestration frameworks.
• Implement tool integrations using MCP/FastMCP or comparable protocols.
• Build and integrate REST APIs, enterprise systems, databases, and SQL-based solutions.
• Develop RAG solutions using structured and unstructured data sources.
• Design secure data-access patterns with authentication and enterprise security.
• Implement AI evaluation, monitoring, tracing, and observability with LangSmith, W&B, OpenTelemetry.
• Establish mechanisms to evaluate LLM accuracy, reliability, latency, cost, and performance.
• Incorporate HITL into AI workflows where appropriate.
• Apply AI governance, privacy, security, and compliance throughout development.
• Collaborate with stakeholders to identify opportunities and deliver AI solutions.
• Act as forward-deployed engineer, prototyping and iterating with stakeholders.
• Troubleshoot, optimize and improve AI applications in production.
• Contribute to documentation, architecture decisions, and development standards.

Skills

Python

AI/LLM apps

APIs

SQL

LangGraph

MCP/FastMCP

LangSmith

W&B

OpenTelemetry

HITL

AI governance

Security practices

Forward-deployed eng

Stakeholder mgmt

Tools

LangGraph

MCP/FastMCP

LangSmith

Weights & Biases

OpenTelemetry

OpenAI API

Job description

Seeking an experienced AI/LLM Software Engineer to design, develop, and deploy enterprise-grade AI applications, assistants, agents, and intelligent workflows. The ideal candidate will have strong hands‑on Python and software engineering experience combined with practical expertise in LLMs, RAG, agentic AI, orchestration frameworks, tool integration, and AI observability.

This is a highly collaborative, stakeholder-facing role requiring the ability to translate business requirements into secure, scalable, and production‑ready AI solutions.

Key Responsibilities

• Design and develop enterprise AI/LLM applications, assistants, agents, and intelligent workflows.
• Build scalable and production-ready solutions using Python and modern software engineering practices.
• Develop agentic AI workflows using frameworks such as LangGraph or similar orchestration technologies.
• Implement tool integrations using MCP/FastMCP or comparable protocols and frameworks.
• Build and integrate REST APIs, enterprise systems, databases, and SQL-based solutions.
• Develop RAG (Retrieval-Augmented Generation) solutions using structured and unstructured data sources.
• Design secure data-access patterns incorporating authentication, authorization, and enterprise security requirements.
• Implement AI evaluation, monitoring, tracing, and observability using tools such as LangSmith, Weights & Biases (W&B), OpenTelemetry, or similar platforms.
• Establish mechanisms to evaluate LLM accuracy, reliability, latency, cost, and overall application performance.
• Incorporate Human-in-the-Loop (HITL) processes into AI workflows where appropriate.
• Apply principles of AI governance, responsible AI, privacy, security, and compliance throughout the development lifecycle.
• Collaborate directly with business stakeholders, product teams, architects, and engineering teams to identify opportunities and deliver AI solutions.
• Act as a forward-deployed engineer, working closely with stakeholders to understand problems, prototype solutions, gather feedback, and rapidly iterate.
• Troubleshoot, optimize, and continuously improve AI applications in production environments.
• Contribute to technical documentation, architecture decisions, development standards, and best practices.

Required Qualifications

• 5–8 years of professional software engineering experience.
• Strong hands‑on experience with Python and software development.
• Demonstrated experience building AI/LLM-powered applications in enterprise or production environments.
• Experience developing AI assistants, agents, agentic workflows, or LLM applications.
• Hands‑on experience with MCP/FastMCP or similar tool‑integration technologies.
• Experience with LangGraph or comparable AI/agent orchestration frameworks.
• Strong understanding of APIs, SQL, databases, and enterprise system integration.
• Experience implementing RAG solutions using structured and/or unstructured data.
• Experience with LLM evaluation, monitoring, tracing, or observability tools such as LangSmith, W&B, OpenTelemetry, or similar.
• Understanding of authentication, authorization, secure data access, and enterprise security practices.
• Strong understanding of AI governance, responsible AI, privacy, security, and Human-in-the-Loop concepts.
• Excellent communication and stakeholder‑management skills.
• Ability to work directly with customers/business stakeholders in a forward‑deployed engineering capacity.

Preferred Qualifications

• Experience working with major LLM platforms and APIs such as OpenAI, Azure OpenAI, Anthropic, or similar.
• Experience with vector databases, embeddings, semantic search, and retrieval pipelines.
• Experience deploying AI applications in cloud environments such as Azure, AWS, or GCP.
• Familiarity with CI/CD, Git, containers, and modern DevOps practices.
• Experience building enterprise-grade AI solutions with strong emphasis on security, scalability, reliability, and governance.
• Experience working in consulting, professional services, or customer‑facing engineering environments.

Key Technologies

Python | LLMs | Generative AI | AI Agents | AI Assistants | MCP / FastMCP | LangGraph | RAG | APIs | SQL | Databases | LangSmith | W&B | OpenTelemetry | Authentication | Authorization | AI Governance | Responsible AI | HITL | Enterprise Integration