Full Stack Software Engineer, AI Integration
Core
Architect AI-native applications where LLMs serve as the core engine, designing autonomous agents that navigate complex business logic and interact with live data via the Model Context Protocol (MCP).
Role type
Senior Full Stack AI Engineer (Agentic Orchestration)
Builds
Autonomous agent systems, high-concurrency back-end services, and streaming front-end UIs for real-time AI interactions.
Domain
Automotive / Generative AI / Agentic Systems
Deliverable
production ML models | product features | infrastructure
Required skills
Agentic orchestration (LangChain, LlamaIndex, CrewAI), Tool-use architecture, MCP server implementation, Async Python (FastAPI) or Java (Spring Boot), Real-time streaming UIs (React/Angular), RAG pipelines (re-ranking, embedding optimization), Context window optimization, AI evaluation & observability, Cloud infrastructure (GCP/AWS), DevOps (Kubernetes, Terraform, CI/CD), Vector databases (pgvector, Chroma, Qdrant, Pinecone)
Preferred skills
MCP expertise, Prompt Engineering as Code, Long-Context model strategies
Technologies
LangChain, LlamaIndex, CrewAI, FastAPI, Spring Boot, React, Angular, PostgreSQL, pgvector, Chroma, Qdrant, Pinecone, GCP Vertex AI, AWS Bedrock, Docker, Kubernetes, Terraform, GitHub Actions, Jenkins
Responsibilities
Design self-correcting agentic loops and tool-calling capabilities for LLMs; Develop high-concurrency back-end services optimized for token streaming; Build responsive stateful UIs handling complex AI interactions; Implement advanced RAG pipelines with re-ranking and query transformation; Establish automated AI benchmarking for hallucination and latency; Manage CI/CD pipelines including vector database migrations.
Seniority
Senior, hands-on IC
