AI Engineer (10+years)

AI Engineer
Remote
Only W2

 We are looking for a hands-on AI Engineer with 3+ years of software engineering, data science, or AI/ML experience to help design and build a new enterprise AI application from the ground up. The engineer will work with AI architects, product leaders, business analysts, and application developers to build production-ready capabilities using Generative AI, Retrieval-Augmented Generation (RAG), Agentic AI, Machine Learning, APIs, and enterprise data sources.

Key Responsibilities:

1. Generative AI Application Development

Develop enterprise applications leveraging Large Language Models (LLMs) and Generative AI.

Integrate commercial and open-source models into business applications.

Build prompt templates, structured prompts, system prompts, and reusable prompt libraries.

Implement structured outputs and reliable LLM-based workflows.

Evaluate different models based on accuracy, latency, cost, and business requirements.

Develop mechanisms to reduce hallucinations and improve response quality.

Implement guardrails and validation mechanisms for enterprise AI applications.

2. Retrieval-Augmented Generation (RAG)

Build RAG pipelines that allow LLMs to securely retrieve and reason over enterprise information.

Ingest structured and unstructured content including PDFs, Word documents, spreadsheets, databases, and knowledge repositories.

Develop document parsing, chunking, metadata extraction, embedding, and indexing pipelines.

Implement vector and hybrid search.

Work with vector databases and enterprise search technologies.

Improve retrieval quality through metadata filtering, query transformation, reranking, and retrieval optimization.

Build citation and source-traceability capabilities so users can verify AI-generated answers.

Evaluate RAG solutions using retrieval and answer-quality metrics.

3. Agentic AI Development

Build AI agents capable of reasoning, retrieving information, calling tools, and performing business actions.

Develop multi-step agent workflows that combine LLM reasoning with APIs, databases, enterprise applications, and business rules.

Implement tool/function calling for enterprise operations.

Develop agents that can determine the appropriate next action based on business context.

Implement human-in-the-loop approval mechanisms for sensitive or high-impact actions.

Build agent memory, state management, workflow orchestration, exception handling, and retry mechanisms.

Assist in developing multi-agent architectures where specialized agents collaborate to complete business processes.

Required Skills

2+ years of experience in AI/ML, Data Science, Software Engineering, or related development roles.

Strong programming skills in Python.

Experience working with REST APIs and JSON.

Experience with LLMs and Generative AI application development.

Understanding of embeddings, vector search, semantic search, and RAG.

Familiarity with agent frameworks such as LangChain, LangGraph, Semantic Kernel, or similar technologies.

Working knowledge of Machine Learning concepts and algorithms.

Experience working with SQL and relational databases.

Understanding of Git and modern software development practices.

Ability to troubleshoot complex application and integration issues.

Strong analytical and problem-solving skills.

Best Regards,
Praveen