Generative AI Engineer

Company Description

Anelyz is a market research and research technology company helping organizations execute research faster, improve data quality, and make better-informed decisions.

We combine research technology, global audience access, fieldwork intelligence, and data quality solutions to support agencies, brands, consultants, and research teams across the research lifecycle. Our technology helps teams design and deploy studies, monitor fieldwork, identify quality and operational signals, and turn complex data into clearer evidence for decision-making.

Anelyz is also advancing how respondents share feedback through video and audio responses supported by AI-assisted analysis.

Research at Decision Speed.

Role Description

We are looking for a Generative AI Engineer to help build AI-powered capabilities across Anelyz's research technology products.

This is a full-time remote role for an engineer who enjoys turning modern AI models into reliable, production-ready product experiences.

You will work across large language models, multimodal AI, retrieval, orchestration, evaluation, and application integration to develop intelligent features for research automation, respondent analysis, data quality, survey workflows, and insight generation.

This is a hands-on engineering role. You will contribute directly to production systems, experiment with new AI capabilities, evaluate model performance, and work closely with product and engineering teams to turn ideas into scalable product features.

Key Responsibilities

• Build and integrate Generative AI features into production SaaS applications.
• Develop workflows using large language models for text analysis, summarization, classification, extraction, and intelligent automation.
• Work with multimodal AI for text, image, audio, and video-based use cases.
• Build and optimize RAG pipelines, embeddings, vector search, and retrieval workflows.
• Integrate external AI APIs and model providers into product applications.
• Design prompt and orchestration strategies for reliable, structured, and repeatable outputs.
• Evaluate model quality, hallucination risk, latency, cost, and output consistency.
• Build safeguards, validation layers, and fallback mechanisms for production AI features.
• Collaborate with product, engineering, and research teams to identify practical AI use cases.
• Develop AI-powered capabilities for research workflows, open-ended response analysis, data quality, and automation.
• Monitor and improve AI feature performance based on usage, feedback, and evaluation results.
• Document AI workflows, model behavior, and engineering decisions.

Must Have Qualifications

• 3+ years of professional software, AI, machine learning, or applied AI engineering experience.
• Hands-on experience integrating LLMs or Generative AI models into real applications.
• Strong Python skills.
• Experience working with AI APIs such as OpenAI, Anthropic, Google Gemini, or similar model providers.
• Understanding of prompt engineering, structured outputs, model evaluation, and orchestration workflows.
• Experience with embeddings, vector databases, semantic search, or RAG-based applications.
• Experience building APIs or backend services for AI-enabled applications.
• Strong problem-solving and debugging skills.
• Understanding of model limitations, hallucinations, privacy, security, and responsible AI practices.
• Ability to work independently in a remote environment and collaborate effectively with product and engineering teams.

Preferred Qualifications

• Experience with multimodal AI involving text, image, audio, or video.
• Experience with frameworks such as LangChain, LlamaIndex, Semantic Kernel, or similar.
• Experience with vector databases such as Pinecone, Weaviate, Qdrant, pgvector, or similar.
• Familiarity with model evaluation frameworks and LLM observability.
• Experience with Node.js, TypeScript, or full-stack development.
• Familiarity with AWS, Azure, GCP, Firebase, or other cloud platforms.
• Experience building production SaaS products.
• Experience with speech-to-text, audio analysis, video analysis, or computer vision.
• Familiarity with fine-tuning, model adaptation, or open-source models.
• Experience with research, survey, analytics, or data quality applications is an advantage.

What We Value

We value engineers who are curious about what AI can do, but equally thoughtful about where it should and should not be used.

You should care about reliability, accuracy, user trust, and building AI capabilities that solve real problems rather than adding AI for its own sake.

We value experimentation, strong engineering fundamentals, ownership, clear communication, and the ability to turn emerging technology into useful product experiences.