What are the responsibilities and job description for the AI Solutions Engineer / GenAI Application Developer position at Concent Software Solution LLC?
Job Details
AI Solutions Engineer / GenAI Application Developer
Jersey City,NJ
12 Years of Experience
Experience in Build Agents
Experience in building the knowledge base
Experience in building apps in Azure AI components
We are seeking an experienced AI Solutions Engineer with strong hands-on experience in building Generative AI applications, designing agentic AI workflows, and deploying solutions on Microsoft Azure. AI modeling experience is mandatory, including fine-tuning, training, evaluation, or customizing models for enterprise use cases. The ideal candidate will also have exposure to orchestration tools such as Semantic Kernel.
Key Responsibilities
- Design and develop end-to-end GenAI-powered applications including LLM-based reasoning, summarization, classification, planning, and multimodal workflows.
- Build and orchestrate agentic AI systems, including planning, tool calling, memory, and multi-step autonomous workflows.
- Develop, fine-tune, evaluate, and optimize AI/ML or LLM models for domain-specific tasks.
- Integrate enterprise data with LLMs using frameworks such as Semantic Kernel, Azure OpenAI, vector databases, and retrieval pipelines.
- Architect and deploy scalable AI microservices and cloud applications using Azure services (Functions, App Service, AKS, Service Bus, Cosmos DB, etc.).
- Implement prompt engineering, model evaluation, A/B testing, observability, and quality assurance for AI features.
- Ensure model performance, safety, governance, and compliance with enterprise AI standards.
- Collaborate with product and architecture teams to translate business requirements into production AI solutions.
Required Skills & Experience
- AI modeling experience is mandatory, including one or more of:
- Fine-tuning LLMs or transformer models
- Training or retraining machine learning models
- Building evaluation pipelines for LLMs
- Implementing RAG, adapters (LoRA), or domain customization techniques
- 3–8 years of software development experience (C#, .NET, Python, or JavaScript preferred).
- Hands-on experience building Generative AI applications, including LLM orchestration, tool calling, or RAG.
- Solid understanding of agentic AI concepts (planning, memory, autonomous tasks, multi-agent patterns).
- Experience building and deploying applications on Microsoft Azure.
- Exposure to Semantic Kernel or similar orchestration frameworks (LangChain, PromptFlow, AutoGen, Haystack).
- Strong knowledge of cloud-native architectures, microservices, REST APIs, and event-driven design.
- Experience with embeddings, vector stores, prompt engineering, and model performance tuning.
Preferred Qualifications
- Experience with Azure AI Studio, Azure OpenAI, or OpenAI APIs.
- Experience with CI/CD pipelines (GitHub Actions, Azure DevOps).
- Understanding of Responsible AI, model safety, and secure deployment practices.
- Background in data engineering, distributed systems, or architecting enterprise-grade applications.
Soft Skills
- Strong communication and documentation abilities.
- Ability to simplify complex AI concepts for stakeholders.
- Analytical, curious, and comfortable working in fast-paced environments.
- Collaborative mindset within agile, multi-disciplinary teams.
API Kong Developer
Remote
10 Years of Experience required
Experienced senior engineers to design, implement, and manage the Kong Platform internally, enabling scalable API-led integration across the enterprise.
Architect and implement best practices across platform environments
Define and enforce platform-wide patterns, standards, and governance
Lead automation of CI/CD pipelines for API and proxy deployment across federated teams and platform operations
Provide technical guidance to federated teams and developers
Lead capacity planning, scaling strategies, and performance optimisation efforts
Collaborate with ITRMS for platform security, auditability, and compliance
End-to-end Observability of the platform
Support and execute on platform roadmap evolution: version upgrades, new capabilities, etc.
