Full Stack Gen AI Engineer

We are looking for a highly skilled Full Stack Gen AI Engineer with 7+ years of experience in software engineering, with a heavy focus on Python, AWS infrastructure, and Generative AI. The ideal candidate will be responsible for building high-performance API services and implementing complex RAG and Agentic AI architectures. Key Requirements:

Experience: Minimum of 7+ years of professional experience in software development and AI engineering.

API & Backend: Expert in building high-performance API / microservices using Python (FastAPI) deployed on AWS Fargate (ECS) (Most Critical).

Generative AI Integration: Hands-on experience integrating Generative AI/LLM APIs, AWS Bedrock, and other model providers.

Infrastructure & DevOps: Experience with DevOps, CI/CD pipelines, and ML pipelines within the AWS ecosystem.

Agentic AI: Exposure to building Gen AI/Agentic AI applications, managing efficiency, latency, and backend infrastructure.

Technical Standards: Strong Python programming skills with a deep understanding of OpenAI API standards, JSON RESTful design, and LLM orchestration.

Preferred Skills: Experience working with Bedrock Agent/Core services is a significant plus.

Core Focus

Areas & Expectations

Candidates will be expected to demonstrate deep technical proficiency in the following areas:

• Retrieval-Augmented Generation (RAG)

Ability to design and implement end-to-end RAG pipelines, including retrievers, vector stores (e.g., Pinecone, Weaviate, or pgvector), and generators.

Expertise in latency optimization and relevance tuning to ensure production-grade performance.

Strategic approach to document chunking and embedding, balancing granularity with semantic coherence.

2.

Agent

Development

Practical experience developing autonomous or semi-autonomous agents using frameworks such as LangChain, CrewAI, or Semantic Kernel.

Ability to manage orchestration, tool integration, and robust error handling for non-deterministic AI outputs.

Proficiency in managing memory and context (episodic vs. long-term) in multi-turn interactions and external API interfacing.

• Evaluation and Optimization

Familiarity with evaluation frameworks (e.g., RAGAS, TruLens) to assess performance, grounding accuracy, and hallucination detection.

Ability to iterate systems based on performance metrics and continuous improvement practices.