Note: The job is a remote job and is open to candidates in USA. Sciemo builds AI solutions for consumer brands, using machine learning, generative AI, agent-based systems, and graph technologies to improve business decision-making across the IBP process. The AI Engineer will design, build, deploy, evaluate, monitor, and optimize the LLM and agent systems powering Sciemo's products, while collaborating with technical teams, customers, and stakeholders to deliver measurable business impact.
Responsibilities
- Architect, build, and deploy LLM- and agent-based products on cloud infrastructure (AWS or similar)
- Design multi-agent systems, tool use, and orchestration patterns for complex business workflows
- Build retrieval and grounding pipelines over customer data, including graph-based and hybrid retrieval approaches
- Create automated pipelines for deployment, prompt/model versioning, and continuous performance monitoring
- Build rigorous evaluation frameworks — offline benchmarks, online metrics, and human-in-the-loop review — for systems whose outputs aren't trivially gradeable
- Design for reliability and fault tolerance: fallbacks, guardrails, cost and latency control, and graceful degradation
- Continuously optimize inference workflows for efficiency, robustness, and performance in production
- Translate complex business problems into AI solutions, including scoping, experiment design, and roadmap planning
- Develop interpretable, modular, and scalable systems that deliver measurable business value
- Work directly with customers and stakeholders to ensure deployed systems achieve their intended impact
- Stay current with advancements in LLMs, agent architectures, retrieval, and graph AI
- Propose and prototype new approaches for integrating emerging techniques into production products
- Develop methods to quantify and communicate AI performance and business ROI
- Promote responsible, ethical, and impactful AI practices across the organization
Skills
- Proven track record of launching LLM- or agent-based products into production — not just prototypes
- Strong production-grade Python; comfort with the modern GenAI tooling ecosystem
- Hands-on experience with agent frameworks, tool use, structured output, RAG, and prompt engineering at production scale
- Experience building evaluation systems for generative outputs, and using them to drive real improvement
- Familiarity with the broader ML stack (PyTorch, scikit-learn, SQL, Spark) and with fine-tuning or model adaptation where it's warranted
- Experience designing and managing orchestration workflows and versioned pipelines (Airflow, ZenML, Kedro, dbt, etc.)
- Strong problem-solving skills, adaptability, and a "hacker" mentality
- Excellent communication skills — able to work with both technical and non-technical stakeholders
- Demonstrated thought leadership and innovation in applied AI
- Hybrid role based in New York City; open to remote U.S. candidates willing to travel monthly to our NYC office
Benefits
- Hybrid role based in New York City; open to remote U.S. candidates willing to travel monthly to our NYC office.
Company Overview
Company H1B Sponsorship