AI Developer Job Description

Responsibilities:

• Architect and deploy AI agents that automate manual and repetitive processes.
• Fine-tune large language models (LLMs) such as GPT-4, LLaMA, and Claude for specific business needs.
• Build retrieval-augmented generation (RAG) pipelines using frameworks like LangChain or similar solutions.
• Seamlessly integrate AI solutions with existing platforms and data infrastructures, using RESTful APIs and tools such as PostgreSQL, Snowflake, and Retool.
• Develop performance monitoring interfaces for AI agents to ensure reliability and operational value.
• Collaborate with cross-functional teams to understand core business workflows and apply AI-driven automation.
• Stay current on the latest advancements in AI/ML, LLMs, and agent-based architectures.
• Proactively introduce new ideas, tools, or techniques to improve AI performance and scalability.
• Design modular and reusable AI components to enable rapid deployment across multiple domains.
• Implement evaluation pipelines to continuously benchmark agent performance against real-world tasks.
• Contribute to system architecture decisions related to inference infrastructure, latency optimization, and fallback strategies.
• Lead or participate in internal AI reviews and knowledge-sharing sessions to upskill team members and align on best practices.

Qualifications/Experience:

• 5+ years of Python programming experience, focused on AI, machine learning, and NLP applications.
• Proven track record implementing and fine-tuning LLMs (e.g., GPT, Claude, LLaMA) including experience with prompt engineering.
• Hands-on experience with LLM orchestration frameworks such as LangChain or LlamaIndex.
• Experience building and optimizing Retrieval-Augmented Generation (RAG) pipelines.
• Proficiency with vector databases and embedding models.
• Solid SQL skills and database integration experience (PostgreSQL, Snowflake, etc.).
• Familiarity with metrics and methodologies to evaluate LLM performance in production.
• Version control proficiency (e.g., Git) and collaborative development workflows.
• Experience deploying LLM applications in cloud environments (AWS, Google Cloud Platform, or Azure) with attention to cost, scalability, and latency.
• Familiarity with agent frameworks or libraries (e.g., AutoGPT, CrewAI, or LangGraph) and ability to design multi-step reasoning flows.
• Demonstrated ability to work with unstructured data sources and implement data pre-processing and transformation pipelines.
• Strong debugging, profiling, and optimization skills for both training and inference pipelines.

Nice to Haves:

• Experience designing interfaces with low-code platforms like Retool.
• Background in extracting structured data from unstructured sources (PDFs, emails, etc.).
• Understanding of API cost optimization strategies for LLM usage.
• Startup or agile team experience, especially in building MVPs from scratch.
• Contributions to open-source AI/NLP projects or active participation in the AI research community (e.g., papers, blogs, talks).
• Experience implementing AI safety techniques such as guardrails, prompt injection prevention, and hallucination mitigation.
• Exposure to multimodal AI (e.g., combining text with image, audio, or tabular data inputs).
• Understanding of real-time AI use cases or streaming data environments.