AI Full Stack Engineer

Job Description

About the Role

We are looking for a hands-on AI Full Stack Engineer to join our growing AI Center of Excellence. In this role, you will design, build, and operationalize intelligent AI agents and LLM-powered solutions that drive real business impact. You will work across the full stack — from cloud infrastructure and backend services to front-end interfaces and AI frameworks — owning the complete lifecycle from prototype to production deployment.

Key Responsibilities

•  Design and develop AI agents — including autonomous, multi-step, and tool-using agents — using AWS Bedrock and leading agentic frameworks.

•  Build, fine-tune, and integrate Large Language Models (LLMs) and Small Language Models (SLMs) into production workflows.

•  Develop full stack applications — from responsive front-end UIs to backend services and agent orchestration layers — using Node.js, Python, and modern front-end frameworks.

•  Implement agent monitoring, observability, and evaluation pipelines using tools such as Fiddler AI and comparable platforms.

•  Collaborate with product and engineering teams to translate business requirements into robust AI-powered features.

•  Establish best practices for responsible AI, prompt engineering, model evaluation, and agent safety.

•  Continuously evaluate emerging models, frameworks, and tooling to keep the platform at the cutting edge.

•  Contribute to internal documentation, architecture reviews, and knowledge sharing across the team.

Required Qualifications

Cloud & Infrastructure

•  AWS Bedrock — hands-on experience building and deploying models and agents on the Bedrock platform (foundation model access, Knowledge Bases, Agents for Bedrock).

•  Familiarity with broader AWS ecosystem (Lambda, S3, IAM, API Gateway, etc.).

Agent Development

•  Proven, hands-on experience building AI agents — including autonomous agents, tool-calling agents, ReAct / plan-and-execute patterns, and multi-agent orchestration.

•  Experience with agentic frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or AWS Bedrock Agents.

•  Strong understanding of agent memory, context management, and tool use.

Languages & Frameworks

•  Python — proficient; used for ML pipelines, agent logic, data processing, and scripting.

•  Node.js — proficient; used for API development, backend services, and agent integration layers.

•  Front-end — working knowledge of a modern front-end framework (React, Next.js, or Vue) to build AI-powered user interfaces and chat/agent experiences.

LLM / SLM Expertise

•  Hands-on experience working with Large Language Models (e.g., Claude, GPT-4, Llama, Mistral) and Small Language Models (e.g., Phi-3, Gemma, Mistral 7B).

•  Practical knowledge of prompt engineering, few-shot learning, RAG (Retrieval-Augmented Generation), and fine-tuning workflows.

Monitoring & Observability

•  Experience with Fiddler AI or comparable agent/model monitoring tools (e.g., LangSmith, Arize, Weights & Biases, Helicone).

•  Ability to define and track agent performance metrics: accuracy, latency, hallucination rate, tool-call success, and cost.

Preferred Qualifications

•  Experience with vector databases (Pinecone, pgvector, OpenSearch, Weaviate) for semantic search and RAG pipelines.

•  Familiarity with MLOps practices — CI/CD for models, model versioning, A/B evaluation.

•  Exposure to multi-modal models (vision + language).

•  Prior work in an AI product or platform team at scale, ideally in a full stack capacity.

•  Experience integrating AI capabilities (streaming responses, tool calls, agent UIs) into front-end applications.

•  AWS certifications (e.g., AWS Certified Machine Learning — Specialty) are a plus.