Generative AI Applications Engineer (Agents & RAG)

End-to-end ownership of production systems: integration → deployment → observability → incident response.

Hands-on experience with LLMs, transformer based apps, and RAG in production.

Experience with vector search and retrieval (Pinecone, Weaviate, OpenSearch, pgvector, FAISS/Chroma) and grounding AI in enterprise/mission data.

Integration with leading cloud AI services or on prem inference stacks

Background in LLM evaluation, prompt authoring/testing, A/B experimentation, and LLM Ops.

Responsible AI expertise (privacy, security, bias, transparency, human in the loop) and data governance.

You’ll turn mission needs into secure, reliable, and scalable GenAI applications no model training required.

This is a hands-on role across agentic workflows, RAG, prompt/policy design, LLM evaluation, and platform integration. You’ll own the end-to-end path from use case evaluation → production deployment → operational excellence, partnering with product, security, data, and SRE to ship features safely and at scale.

Design & ship mission grade GenAI: Build agentic workflows and RAG systems tailored to mission data and environments; target low hallucination, tight p95 latency, and predictable cost.

Agent frameworks & orchestration: Apply patterns from LangChain/LlamaIndex/Semantic Kernel; design task decomposition, tool use, guardrails, and recovery/fallback strategies.

Platform integration (no model training): Implement with AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra, and managed services (e.g., Document AI, Gemini, Gemma).

LLM selection & evaluation: Compare models for quality, safety, latency, cost; author/test prompts & policies; deploy with observability and safe rollback/fallback.