AI Engineer: Autonomous Agents & RAG Systems

Confie; United States; On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Health insurance

Bonuses

Paid time off

Remote/hybrid options

401k match

Scholarship fund

Gym reimbursement

DEI commitment

Employee assistance

Extended insurance plans

Job summary

Confie is seeking an AI Engineer to design, develop, and deploy production-grade AI solutions, including autonomous agents and RAG-based systems, leveraging LangGraph, AutoGen, CrewAI, and OpenAI Assistants API. You will enable tool use, memory management, and enterprise integrations while ensuring quality and security.

You will work with cloud platforms like Snowflake, Azure, AWS, and Databricks, focusing on scalable, observable AI systems and measurable business impact.

Qualifications

• Minimum of 3 years of professional experience in AI engineering or related roles.
• 3+ years experience developing AI/ML solutions on platforms such as Snowflake, Azure, AWS, OpenAI, Databricks, or similar.
• 2+ years hands-on experience with Generative AI including LLM application development, RAG systems, and production deployments.
• Experience with agentic AI frameworks (LangGraph, AutoGen, CrewAI, OpenAI Assistants API) and multi-agent orchestration.
• Proficiency in Python, LangChain/LlamaIndex, and vector databases (Pinecone, Weaviate, Chroma, pgvector, Snowflake).
• Expertise in prompt engineering including chain-of-thought, few-shot learning, and structured outputs (JSON mode, function calling).
• Experience with evaluation frameworks for Generative AI (RAGAs, TruLens, DeepEval) in the context of text generation.
• Understanding of AI safety concepts including guardrails, content filtering, hallucination mitigation, and red-teaming.
• Experience with data preprocessing, feature engineering, and model evaluation techniques.
• Solid understanding of software engineering principles and best practices.
• Experience bringing GenAI projects through production and implementation with measurable business impact.

Responsibilities

• Design, develop, and deploy production-grade AI solutions including autonomous agents, generative AI applications, and RAG-based systems.
• Design and deploy autonomous AI agents using frameworks like LangGraph, AutoGen, CrewAI, or OpenAI Assistants API for multi-step reasoning and task execution.
• Implement function calling, tool use, and API integrations enabling LLMs to interact with enterprise systems, databases, and external applications.
• Design agent memory systems including conversational memory, long-term knowledge retention, and context management strategies.
• Build advanced RAG systems with vector databases, hybrid search (dense + sparse retrieval), and reranking for domain-specific chatbots and knowledge retrieval.
• Develop generative AI solutions for text generation, summarization, audio-to-text transcription, and call center conversation insights using LLMs.
• Develop advanced prompting strategies including chain-of-thought reasoning, few-shot learning, and structured output generation.
• Integrate with AI platforms including Snowflake Cortex, OpenAI, Azure AI Studio, AWS Bedrock, and Anthropic Claude.
• Implement AI observability, guardrails, and evaluation frameworks (RAGAs, TruLens, DeepEval) to ensure quality, safety, and reliability.
• Conduct experiments and fine-tune models using techniques like LoRA and QLoRA to optimize performance for domain-specific use cases.
• Deploy production solutions using containerization (Docker, Kubernetes), CI/CD pipelines, and cloud-native architectures.
• Continuously monitor the performance of AI solutions and implement improvements.
• Create high-level and detailed design documentation for AI solutions, including architecture diagrams and technology selection rationale.
• Collaborate with cross-functional teams to identify and prioritize high-impact AI opportunities that drive significant business value.
• Mentor and provide guidance to junior team members; participate in code reviews and maintain high-quality engineering standards.
• Keep updated with advances in AI technology and find opportunities to upgrade existing solutions.
• Adhere to best practices in data privacy and security when working with sensitive data.

Skills

3+ years experience AI engineering

AI/ML solutions on Snowflake/AWS/Azure

Generative AI & LLM deployments

Agentic AI frameworks (LangGraph, Auto

Python, LangChain/LlamaIndex

Prompt engineering (chain-of-thought,

AI evaluation frameworks (RAGAs, Deep)

AI safety concepts & red-teaming

Data preprocessing & feature eng.

Production deployment & software best

Education

Bachelor's degree in CS/Data Science or related

Certifications in AI/ML on cloud platforms

Tools

Snowflake

Azure

AWS

OpenAI

Databricks

Job description

Confie is seeking an AI Engineer to design, develop, and deploy production-grade AI solutions, including autonomous agents and RAG-based systems, leveraging LangGraph, AutoGen, CrewAI, and OpenAI Assistants API. You will enable tool use, memory management, and enterprise integrations while ensuring quality and security.

You will work with cloud platforms like Snowflake, Azure, AWS, and Databricks, focusing on scalable, observable AI systems and measurable business impact.