This is a fully remote position, open to applicants in Poland.

• Integrate AI capabilities into current Python, Node.js, and Ruby codebases

• Develop features powered by LLMs, including chat, summaries, classification, smart search, and document Q&A

• Create efficient RAG pipelines utilizing embeddings and vector search technology

• Collaborate with vector databases such as pgvector, Pinecone, and Qdrant

• Establish secure and dependable LLM endpoints (OpenAI, Anthropic, Azure)

• Engage directly with clients to define AI features and minimize manual tasks

• Guide clients on when to refrain from using AI and address trade-offs regarding latency, accuracy, and cost

• Strong foundation in software engineering with expertise in Python, Node.js, or Ruby

• Practical experience in integrating LLM APIs into live production environments (OpenAI, Anthropic, or equivalent)

• Capability to devise practical AI solutions within existing systems

• Proficiency in constructing RAG pipelines, embeddings, and vector searches

• Awareness of the cost, latency, and reliability challenges associated with AI systems

• Ability to work autonomously with clients while managing realistic expectations

• Experience in big data or data pipeline development is highly advantageous

• Proficiency in English at B2/C1 level

• Availability for part-time or full-time work (B2B contract)

• Competitive compensation package

• Opportunity to work on innovative AI projects

• Flexible working hours and remote work options

• Collaborative and inclusive work environment

LLM Engineer, Freelancer

People also viewed