> Markdown version of [/jobs/ext/95393-generative-ai-engineer](https://www.wearedevelopers.com/jobs/ext/95393-generative-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Generative AI Engineer - **Company:** SATCON Inc - **Location:** Charlotte, NC, United States - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Microsoft Azure, Data Governance, Dependency Injection, Github, Design of User Interfaces, Human-Computer Interaction, Python (Programming Language), PostgreSQL, MongoDB, NoSQL, Software Architecture, Redis, Software Engineering, SQL Databases, Management of Software Versions, WebSocket, Openapi, RxJS, Large Language Models, Multi-Agent Systems, Model Validation, Generative AI, Backend, Fastapi, Build Management, AI Platforms, AngularJS, Kubernetes, Machine Learning Operations, Front End Software Development, Api Design, Restful APIs, Docker - **Published:** May 28, 2026 - **Apply:** https://www.dice.com/job-detail/e159ec8d-8c89-4cec-9e4c-c3a421e6b929 ## About the Role Overall Experience: 8+ Years (with strong Python expertise) GenAI Experience: 2+ Years (in Production Environments, not just POCs), · Experience: 8+ years of total software engineering experience; 2+ years of hands-on, production-level Generative AI experience. · Core GenAI Stack: LangChain, LangGraph, LLM APIs (OpenAI, Anthropic, Azure, Bedrock), and Vector Stores (Chroma, Pinecone, Weaviate, pgvector). · Backend & Protocol: Python 3.10+ (async/await, Pydantic v2), FastAPI, and hands-on experience building/deploying MCP servers or equivalent context-injection frameworks. · Frontend: Angular 15+ (components, services, RxJS, and signals) to successfully bridge backend AI services with the user interface. · Data & Infrastructure: SQL + NoSQL (PostgreSQL, MongoDB, Redis), Docker, Kubernetes, and GitHub Actions CI/CD. · Preferred (Plus) Skills · Experience with graph-based architectures for complex, cyclic reasoning tasks. · Familiarity with fine-tuning workflows (LoRA/QLoRA, PEFT, DPO/RLHF) and distributed inference (vLLM, TGI, Triton). · Prior experience in regulated industries (Banking, FinTech, Healthcare) with awareness of model risk management frameworks (e.g., SR 11-7). ## Description · GenAI Solution Engineering & Advanced RAG · Orchestration: Design and build production GenAI applications using LangChain and LangGraph for multi-agent, stateful, and graph-based workflows. · RAG Optimization: Develop and optimize RAG pipelines including advanced patterns like HyDE, re-ranking, hybrid search, multi-hop retrieval, and RAPTOR hierarchical summarization. · API Development: Build and expose GenAI capabilities as RESTful and streaming APIs using FastAPI (with async support, dependency injection, and OpenAPI documentation). · MCP Server Development & LLMOps · Context Architecture: Architect and maintain Model Context Protocol (MCP) servers to securely connect LLMs to heterogeneous enterprise data sources (SQL, NoSQL, APIs). · Observability: Integrate systems with frameworks like LangSmith, Helicone, Arize, or OpenTelemetry for tracing, latency profiling, and prompt lineage. · Guardrails & Monitoring: Own prompt versioning, model evaluation (RAGAS, ROUGE, BERTScore), and implement guardrails (Guardrails AI, NeMo Guardrails) for PII redaction and toxicity filtering. Full-Stack Integration & Governance Angular Frontend: Develop Angular-based user interfaces (chat UIs, agent monitors, dashboards) and consume FastAPI streaming endpoints (SSE / WebSockets) for real-time token streaming. Platform Governance: Contribute to architectural decisions around model routing, semantic caching (Redis), and multi-tenant isolation while ensuring compliance with enterprise data governance. ## Related Videos - [Leveraging Real time data in FSIs](https://www.wearedevelopers.com/videos/806-leveraging-real-time-data-in-fsis) - [How E.On productionizes its AI model & Implementation of Secure Generative AI.](https://www.wearedevelopers.com/videos/623-how-e-on-productionizes-its-ai-model-implementation-of-secure-generative-ai) - [How to Create New RxJS Operators](https://www.wearedevelopers.com/videos/683-how-to-create-new-rxjs-operators) - [Reducing LLM Calls with Vector Search Patterns - Raphael De Lio (Redis)](https://www.wearedevelopers.com/videos/1714-reducing-llm-calls-with-vector-search-patterns-raphael-de-lio-redis) - [Make it simple, using generative AI to accelerate learning](https://www.wearedevelopers.com/videos/969-make-it-simple-using-generative-ai-to-accelerate-learning) - [Practice makes perfect - when it comes to RxJS](https://www.wearedevelopers.com/videos/1-practice-makes-perfect-when-it-comes-to-rxjs) ## Related Articles - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [Got AI ideas but no money? Here are 10 free ways to level up your AI skills with Google Cloud](https://www.wearedevelopers.com/magazine/600-got-ai-ideas-but-no-money-here-are-10-free-ways-to-level-up-your-ai-skills-with-google-cloud) - [WWC24 Talk - Scott Hanselman - AI: Superhero or Supervillain?](https://www.wearedevelopers.com/magazine/469-wwc24-talk-scott-hanselman-ai-superhero-or-supervillain) - [How to Use Generative AI to Accelerate Learning to Code](https://www.wearedevelopers.com/magazine/530-how-to-use-generative-ai-to-accelerate-learning-to-code) - [The State of WebDev AI 2025 Results: What Can We Learn?](https://www.wearedevelopers.com/magazine/581-the-state-of-webdev-ai-2025-results-what-can-we-learn)