API Centrics
Website:
apicentrics.com
Job details:
Company Description API Centrics is a Salesforce and MuleSoft partner specializing in API-led digital transformation. The company is a trusted provider for MuleSoft projects, supporting organizations with complete project implementation and staff augmentation services. Its team includes multiple Certified Integration Architects, Platform Architects, and Certified Mule 4 Developers, offering deep expertise in integration and API management. API Centrics focuses on delivering seamless, scalable solutions that help clients modernize their systems and improve business performance.
Role Description We are looking for a senior Generative AI expert to lead the design, development, and deployment of LLM-powered solutions — including RAG pipelines, MCP servers, agentic workflows, and intelligent document processing (IDP) — for regulated-industry clients. You will also mentor and train junior engineers
- Architect and build production-grade Gen AI solutions: RAG systems, LLM fine-tuning, prompt engineering frameworks, and evaluation pipelines
- Design and deploy MCP servers and agent-to-agent (A2A) integrations on Azure (Functions, Foundry) and Google Cloud Run
- Build agentic workflows using platforms such as Copilot Studio, Agentforce, LangChain/LangGraph, and MuleSoft Agent Fabric
- Implement AI governance for regulated data (HIPAA/PHI, financial data): minimum-necessary access, identity propagation, audit logging
- Develop and refine IDP pipelines for document extraction (financial statements, healthcare records) with iterative prompt engineering
- Integrate LLM solutions with enterprise systems (Salesforce, SAP, FHIR APIs, RabbitMQ, REST/event-driven architectures)
- Mentor junior AI engineers; review designs, prompts, and code
- Contribute labs, demos, and reference architectures to API Centrics training programs
Qualifications
- Bachelor's/Master's in Computer Science, Engineering, or related field
- 5–8+ years in software/integration engineering; 2+ years building LLM applications in production
- Strong Python (and ideally Java/DataWeave exposure); REST API design
- Hands-on with at least two LLM ecosystems (OpenAI/Azure OpenAI, Anthropic Claude, Gemini, open-source models)
- Proven experience with RAG architecture, vector databases (Pinecone, pgvector, Azure AI Search, etc.), embeddings, and chunking strategies
- Experience with MCP, function/tool calling, and multi-agent orchestration patterns
- Cloud deployment experience (Azure and/or GCP), CI/CD (Azure DevOps preferred), containerization
- Solid grasp of AI security and governance: data privacy, guardrails, hallucination mitigation, evaluation
- Familiarity with APIs, integration platforms, or MuleSoft/Salesforce ecosystems is an advantage.
Click on Apply to know more.