Full Stack Software Engineer, AI Integration

We are moving beyond "Chatbots." We are building AI-native applications where LLMs aren't just features-they are the core engine. As a AI Full Stack Engineer, you will architect systems where autonomous agents navigate complex business logic, utilize the Model Context Protocol (MCP) to interact with live data, and provide users with seamless, real-time streaming experiences.

You aren't just a software engineer; you are an AI Orchestrator bridging the gap between non-deterministic model logic and high-performance software engineering.

We are moving beyond "Chatbots." We are building AI-native applications where LLMs aren't just features-they are the core engine.

1. Agentic Orchestration & Logic

Design Autonomous Loops:
Transition from linear "chain" workflows to self-correcting agentic loops using frameworks like Lang Chain, Llama Index, or CrewAI.

Tool-Use Architecture:
Design and implement robust "tool-calling" capabilities, ensuring LLMs can reliably interact with external APIs and microservices.

MCP Integration:
Build and maintain Model Context Protocol (MCP) servers to bridge the gap between LLMs and our proprietary data silos securely and in real-time.

2. Full Stack AI Delivery

High-Concurrency Back-end:
Develop asynchronous Python (FastAPI) or Java services optimized for long-running AI tasks and token streaming.

Streaming Front-end:
Build responsive, stateful UIs in React or Angular that handle complex AI interactions (streaming text, generative UI components, and multi-modal feedback).

Advanced RAG Pipelines:
Go beyond basic vector search. Implement re-ranking, query transformation, and embedding optimization to maximize retrieval precision.

3. AI Engineering Excellence

Context Optimization:
Master the "Context Window" by implementing prompt compression and "lost-in-the-middle" mitigation strategies.

Evaluation & Observability:
Establish AI Evals to quantify hallucination rates, latency, and cost. Lead the shift from "vibes-based" testing to rigorous, automated AI benchmarking.

Dev Ops/MLOps:
Manage CI/CD pipelines that include vector database migrations and automated prompt versioning.

1. Agentic Orchestration & Logic

Design Autonomous Loops:
Transition from linear "chain" workflows to self-correcting agentic loops using frameworks like Lang Chain, Llama Index, or CrewAI.

Tool-Use Architecture:
Design and implement robust "tool-calling" capabilities, ensuring LLMs can reliably interact with external APIs and microservices.

MCP Integration:
Build and maintain Model Context Protocol (MCP) servers to bridge the gap between LLMs and our proprietary data silos securely and in real-time.

2. Full Stack AI Delivery

High-Concurrency Back-end:
Develop asynchronous Python (FastAPI) or Java services optimized for long-running AI tasks and token streaming.

Streaming Front-end:
Build responsive, stateful UIs in React or Angular that handle complex AI interactions (streaming text, generative UI components, and multi-modal feedback).

Advanced RAG Pipelines:
Go beyond basic vector search. Implement re-ranking, query transformation, and embedding optimization to maximize retrieval precision.

3. AI Engineering Excellence

Context Optimization:
Master the "Context Window" by implementing prompt compression and "lost-in-the-middle" mitigation strategies.

Evaluation & Observability:
Establish AI Evals to quantify hallucination rates, latency, and cost. Lead the shift from "vibes-based" testing to rigorous, automated AI benchmarking.

Dev Ops/MLOps:
Manage CI/CD pipelines that include vector database migrations and automated prompt versioning.