AI engineer, back-end systems (Founding Team)

AI Engineer, Backend Systems Founding Team Location: Delhi Employment type: Full-time Reports to: Founder and CTO About Delphic AI is changing how businesses discover, evaluate and engage with expert knowledge. Delphic works with knowledge-led businesses navigating this shift while protecting the value of their proprietary expertise. We are building the technical infrastructure needed to make complex, evidence-sensitive AI workflows reliable, measurable and useful in production. We are hiring an AI Engineer to help build Delphics core backend systems. You will work at the intersection of large language models, retrieval, evaluation, workflow orchestration and production software engineering. This is an opportunity to shape an AI system from an early stage, work directly with the Founder and CTO, and take meaningful ownership of the technical architecture.

You will design, build and operate production backend systems for data-intensive AI workflows. The technical challenge goes well beyond producing a plausible model response. Our systems must remain reliable when models are non-deterministic, external services change, data is incomplete and outputs require evaluation or human judgement. You will work across backend services, data systems, model integrations, evaluations and infrastructure. You should be comfortable moving between system design, implementation, debugging and production operations. This is an applied AI engineering rolenot a prompt-only, frontend or foundation-model research position.

Design and build scalable backend services and APIs for AI-powered products and internal systems. Build and improve reliable production AI workflows and the backend services that support them. Create robust evaluation frameworks for non-deterministic AI outputs. Develop automated tests, regression suites and representative evaluation datasets. Build observability for model behaviour, system performance, costs, failures and data quality. Design clear data models and interfaces between AI components and conventional software systems. Engineer for retries, idempotency, rate limits, partial failures and changing external dependencies.Improve the accuracy, latency, throughput and cost of production AI workflows. Implement appropriate security and data-isolation controls for customer information. Evaluate new models, tools and infrastructure based on measurable improvements rather than novelty. Work closely with the Founder and CTO on technical priorities, architecture and product decisions. Help establish the engineering practices and technical standards of the early team. You may be a strong fit if You have strong software engineering skills and experience shipping production AI systems. You have hands-on experience with LLMs, agents, evaluations, RAG, tool-calling or AI workflow orchestration. You are strong in Python and comfortable building maintainable backend services. You have experience working with SQL databases, APIs, data models and asynchronous workflows. You understand testing, deployment, monitoring and production debugging. You know that a convincing AI demo and a dependable AI product are very different things. You can design ways to evaluate AI behaviour rather than relying only on subjective inspection. You are comfortable investigating failures across application code, model behaviour, data and infrastructure. You can make thoughtful trade-offs between correctness, latency, cost and engineering complexity. You have a strong ownership mindset and can operate effectively in a fast-moving, early-stage environment. You communicate technical decisions, uncertainties and trade-offs clearly. You are comfortable working with evolving