Generative AI Engineer

Position:

Generative AI Engineer Overall Experience:

8+ Years (with strong Python expertise)

GenAI Experience:

2+ Years (in Production Environments, not just POCs)

Locations:

Charlotte, NC |

New Jersey, NJ Work Mode:

Hybrid (3 days onsite per week)

Employment Type:

Full-Time /

Contract-to-Hire Interview Process:

Includes a mandatory, live hands-on coding round Key Responsibilities

• 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. Required Qualifications

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).